{"id":"W7067262971","doi":"","title":"A Longitudinal Multilevel Extension of the Linear Logistic Test Model to Predict the Instructional Sensitivity of Test Items","year":2019,"lang":"en","type":"article","venue":"Das Repository der Padagogischen Hoschule St. Gallen (Padagogischen Hoschule St. Gallen)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Extension (predicate logic); Test (biology); Item response theory; Sensitivity (control systems); Multilevel model; Logistic regression; Educational testing; Relation (database)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04065803,0.001144222,0.00138443,0.002109321,0.0009393884,0.00194137,0.002877128,0.001119666,0.008648478],"category_scores_gemma":[0.09729216,0.0007452711,0.002688443,0.002531086,0.0007572146,0.002054811,0.002590574,0.004085832,0.001698372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001152804,"about_ca_system_score_gemma":0.002893157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02421429,"about_ca_topic_score_gemma":0.01994184,"domain_scores_codex":[0.9817468,0.01478099,0.0004211398,0.001865402,0.0007164438,0.0004692872],"domain_scores_gemma":[0.8967687,0.08429319,0.005381435,0.008702321,0.003574175,0.001280137],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003152433,0.001744206,0.6768764,0.0003027385,0.005710058,0.0004919224,0.001509163,0.05662273,0.0006758117,0.02020197,0.01366691,0.2190457],"study_design_scores_gemma":[0.0003758142,0.001573576,0.07126968,0.0001660611,0.0011709,0.0002360991,0.0005219999,0.9010848,0.0004137878,0.02022975,0.002842439,0.0001150865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4520422,0.0006735533,0.532846,0.003003803,0.0005104383,0.0009091818,0.005479143,0.001709541,0.00282618],"genre_scores_gemma":[0.8546827,0.0003126136,0.1365769,0.0002521066,0.000142604,0.001385049,0.003171102,0.0001895692,0.003287368],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04065803,"threshold_uncertainty_score":0.2150227,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2688678884034303,"score_gpt":0.4102798062908345,"score_spread":0.1414119178874042,"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."}}