{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003872207,0.000152044,0.0002241645,0.000065163,0.0001429218,0.0000660596,0.0005896612,0.0000391919,0.000005622977],"category_scores_gemma":[0.000007821041,0.00008651849,0.00005444753,0.0002309629,0.00002686456,0.0006305635,0.0001331008,0.0001432039,0.00002729783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004549542,"about_ca_system_score_gemma":0.00002573155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003658754,"about_ca_topic_score_gemma":0.000004515447,"domain_scores_codex":[0.9987009,0.00004185957,0.0002695469,0.0002117727,0.0003875414,0.0003883838],"domain_scores_gemma":[0.9991609,0.00009429955,0.0001286385,0.0003883853,0.0001236385,0.0001041002],"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":[0.00000975187,0.0002400716,0.01122454,0.00002853647,0.0000265064,2.614749e-7,0.01253614,0.8028864,0.001674467,0.1618848,0.0003483929,0.009140185],"study_design_scores_gemma":[0.00008857227,0.0001787113,0.002148466,0.00007699245,0.000005632966,0.000004494672,0.0001797878,0.9876636,0.007593778,0.00002679358,0.001874619,0.0001585145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3776916,0.00003968873,0.616601,0.000154435,0.00009600455,0.0001403819,5.018973e-7,0.00005589453,0.005220463],"genre_scores_gemma":[0.9636482,0.000001033955,0.02577247,0.0001245759,0.00006402496,0.00001205934,4.102065e-7,0.00001178936,0.01036543],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5908286,"threshold_uncertainty_score":0.3528122,"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."}}