{"id":"W4246072790","doi":"10.1007/978-3-642-22362-4_7","title":"Performance Comparison of Item-to-Item Skills Models with the IRT Single Latent Trait Model","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Item response theory; Trait; Artificial intelligence; Statistics; Natural language processing; Programming language; Mathematics; Psychometrics","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":[0.03087876,0.002241576,0.002017674,0.001565793,0.0009472183,0.003052217,0.002824315,0.002256465,0.006570982],"category_scores_gemma":[0.05717335,0.0008112029,0.00251231,0.001531494,0.0006846283,0.00396236,0.001978102,0.002832352,0.0040158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001527949,"about_ca_system_score_gemma":0.002525717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02344544,"about_ca_topic_score_gemma":0.01395868,"domain_scores_codex":[0.9827518,0.01387375,0.0006261771,0.001835549,0.0005857708,0.0003269549],"domain_scores_gemma":[0.9061536,0.08347751,0.0007775946,0.004486223,0.003766819,0.001338294],"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":[0.02327097,0.001672187,0.06713443,0.001082724,0.006160538,0.0003436385,0.001845184,0.4047765,0.002941276,0.00637161,0.02074809,0.4636529],"study_design_scores_gemma":[0.0002802164,0.0006582629,0.01162602,0.00005639171,0.0004271996,0.00008561119,0.0004832993,0.9815552,0.001116584,0.002595669,0.001018481,0.00009699899],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7178804,0.002667331,0.2516743,0.001975896,0.0008833535,0.0004724314,0.004514401,0.01198974,0.00794219],"genre_scores_gemma":[0.9081932,0.0005401305,0.07557087,0.0002700829,0.00009351358,0.0004160656,0.009475997,0.001304656,0.004135482],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03087876,"threshold_uncertainty_score":0.1633045,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04249195637165099,"score_gpt":0.2395953153617875,"score_spread":0.1971033589901365,"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."}}