{"id":"W2004360025","doi":"","title":"Performance Comparison of Item-to-Item Skills Models with the IRT Single Latent Trait Model","year":2012,"lang":"en","type":"article","venue":"","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Item response theory; Computer science; Artificial intelligence; Machine learning; Naive Bayes classifier; Latent variable; Bayesian probability; Statistics; Psychometrics; Mathematics","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":[0.02705203,0.001971275,0.002317501,0.00187969,0.0006669826,0.002106658,0.002540575,0.002786322,0.002395072],"category_scores_gemma":[0.04248665,0.0007079854,0.001727058,0.001756917,0.0006447241,0.003301369,0.001593588,0.002293537,0.001781452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001748253,"about_ca_system_score_gemma":0.001388922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01531393,"about_ca_topic_score_gemma":0.009859846,"domain_scores_codex":[0.9849625,0.01202437,0.0005486162,0.001307327,0.0008945501,0.0002626736],"domain_scores_gemma":[0.9466571,0.04574278,0.001172541,0.002016096,0.00330004,0.001111369],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005607822,0.001201822,0.07656232,0.0007713098,0.002161861,0.0001790281,0.0006969742,0.5788185,0.00184484,0.002606667,0.00721382,0.322335],"study_design_scores_gemma":[0.00006594678,0.0002516628,0.003829139,0.00002946174,0.00007523081,0.00002771211,0.00008052475,0.9941585,0.0003793074,0.0009345797,0.0001375724,0.00003044523],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7254025,0.003622513,0.2551684,0.002141485,0.0004023594,0.000465929,0.001604633,0.007041745,0.004150365],"genre_scores_gemma":[0.9157846,0.0006060486,0.07839033,0.0003170372,0.00009179826,0.0003250375,0.002469421,0.0002183972,0.001797403],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02705203,"threshold_uncertainty_score":0.1430665,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05090242672634297,"score_gpt":0.25507714621778,"score_spread":0.2041747194914371,"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."}}