{"id":"W1987580937","doi":"10.1007/s40593-015-0043-2","title":"Evaluation Methods for Intelligent Tutoring Systems Revisited","year":2015,"lang":"en","type":"article","venue":"International Journal of Artificial Intelligence in Education","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Learning analytics; Matching (statistics); Data science; Artificial intelligence; Machine learning; Educational technology; Intelligent tutoring system; Analytics; Mathematics education","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":[0.01038944,0.0001595572,0.0002655608,0.0007998694,0.00004793791,0.0004605498,0.001151391,0.00008559042,0.000008437501],"category_scores_gemma":[0.003746062,0.0001521202,0.0001341296,0.0004158843,0.00002374425,0.001012288,0.0000782074,0.0002451539,0.0000210068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001229831,"about_ca_system_score_gemma":0.00129541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001271872,"about_ca_topic_score_gemma":0.000005344563,"domain_scores_codex":[0.9965832,0.0005374348,0.001342684,0.0002759377,0.001039046,0.0002216803],"domain_scores_gemma":[0.9916745,0.0003940386,0.0008601348,0.000234288,0.006696211,0.0001408496],"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":[0.00003741098,0.000187853,0.0001854007,0.000009097983,0.0000484124,0.000002451482,0.00321182,0.02658537,0.000623582,0.2482743,0.000138066,0.7206963],"study_design_scores_gemma":[0.000170421,0.0004401354,0.0001484671,0.0009647842,0.00005291882,0.0002057827,0.009421441,0.7063757,0.01752426,0.1479625,0.1163026,0.000431053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005179755,0.002185437,0.9716184,0.0005577088,0.01959402,0.0004369642,8.723478e-7,0.00002175644,0.0004050447],"genre_scores_gemma":[0.7579148,0.0001139908,0.238482,0.0000942312,0.002955168,0.00009426066,0.000007318065,0.00002256622,0.0003156557],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7527351,"threshold_uncertainty_score":0.6203281,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1670174479393055,"score_gpt":0.4703094401001817,"score_spread":0.3032919921608762,"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."}}