{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000831748,0.0005624883,0.00072423,0.0005218719,0.0003187232,0.0002754364,0.003520041,0.0002130475,0.00000537451],"category_scores_gemma":[0.00002626972,0.0003708899,0.0001368923,0.0005217349,0.0004230443,0.0006090586,0.0008608396,0.0008207271,0.00001688198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002223864,"about_ca_system_score_gemma":0.0003116223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003951604,"about_ca_topic_score_gemma":0.00003749127,"domain_scores_codex":[0.9961886,0.0000409916,0.0006699393,0.001209898,0.001201309,0.0006892082],"domain_scores_gemma":[0.9972478,0.0003574868,0.0005220469,0.001267262,0.0004457741,0.0001596294],"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":[0.00001019047,0.00005558425,0.0001521254,0.00004509692,0.00001529982,0.000005826324,0.006649838,0.8164588,0.0001711499,0.03841586,0.000009856842,0.1380104],"study_design_scores_gemma":[0.0001225031,0.0005561814,0.0001253,0.0009663315,0.00001048264,0.00002253214,9.734309e-7,0.9888743,0.002913095,0.00528217,0.0006076152,0.0005185595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004273668,0.0001540788,0.9900793,0.0002174052,0.0005661609,0.0005275361,0.00000355606,0.00009672378,0.004081602],"genre_scores_gemma":[0.8451115,0.000006726762,0.1517505,0.0003273676,0.0001531422,0.00001171496,0.000001157671,0.00003833281,0.002599539],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8408378,"threshold_uncertainty_score":0.9998743,"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."}}