{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09452467,0.001906739,0.003438042,0.006736664,0.0009849764,0.006920955,0.002717335,0.003573836,0.004204625],"category_scores_gemma":[0.19773,0.000862517,0.002014764,0.00683535,0.007192919,0.009036525,0.003367645,0.007630577,0.0009399613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006493872,"about_ca_system_score_gemma":0.003260766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0032545,"about_ca_topic_score_gemma":0.001817774,"domain_scores_codex":[0.8499209,0.1194459,0.006168993,0.004274826,0.0192948,0.0008946416],"domain_scores_gemma":[0.81063,0.1653868,0.003185134,0.004683405,0.01528564,0.0008289856],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001100202,0.00007037753,0.001139517,0.0008061636,0.0002194874,0.00006779109,0.0005305618,0.008840079,0.0002411473,0.7898194,0.007448637,0.1907068],"study_design_scores_gemma":[0.00006906992,0.0001070443,0.0009958635,0.0006259276,0.00005463661,0.0001907569,0.0002800113,0.07061929,0.0003537825,0.9001599,0.02648127,0.00006241685],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.003288648,0.05364696,0.9185388,0.01219362,0.001244043,0.0002647369,0.0001267227,0.000200779,0.01049571],"genre_scores_gemma":[0.2734429,0.02219608,0.6836174,0.003854633,0.004065359,0.00210762,0.0003073641,0.0003922594,0.01001633],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.9054753,"threshold_uncertainty_score":0.4999002,"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."}}