{"id":"W98422573","doi":"10.55016/ojs/ajer.v51i3.55148","title":"The Use of One-, Two-, and Three-Parameter and Nominal Item Response Scoring in Place of Number-Right Scoring in the Presence of Test-Wiseness","year":2005,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Statistics; Item response theory; Test (biology); Psychology; Mathematics; Econometrics; Psychometrics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1223338,0.001936121,0.002166337,0.003406086,0.0006318935,0.002730743,0.003496891,0.001487545,0.004919242],"category_scores_gemma":[0.3239062,0.0008720268,0.002955478,0.003278404,0.002583174,0.004629722,0.004152395,0.002802967,0.002072251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001376535,"about_ca_system_score_gemma":0.001823417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00296787,"about_ca_topic_score_gemma":0.004334479,"domain_scores_codex":[0.8423452,0.1356183,0.005602403,0.006178125,0.009215797,0.001040178],"domain_scores_gemma":[0.66884,0.2696851,0.01576975,0.03232737,0.01143509,0.001942594],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.02428382,0.002120011,0.4126976,0.001344607,0.007503106,0.0009698052,0.004661927,0.0690346,0.008727966,0.02014014,0.005853677,0.4426627],"study_design_scores_gemma":[0.001519182,0.01384762,0.2347441,0.00051469,0.002254432,0.002409217,0.003571797,0.6884251,0.01253483,0.03328406,0.005977747,0.0009171396],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5476765,0.0005310353,0.4403878,0.000631764,0.0002960385,0.001242939,0.0007690859,0.001464665,0.00700018],"genre_scores_gemma":[0.8046908,0.0001652618,0.1913125,0.0001639529,0.00005136237,0.0009106556,0.000811072,0.0003287858,0.001565543],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8776662,"threshold_uncertainty_score":0.6469706,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6230280355567007,"score_gpt":0.5439208949779503,"score_spread":0.07910714057875046,"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."}}