{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02617517,0.00008870276,0.000320639,0.0008114602,0.0001276986,0.0001356733,0.0009184619,0.0000429416,0.000138434],"category_scores_gemma":[0.5613269,0.00004946341,0.00005188298,0.002038566,0.0005418081,0.0004940733,0.0002015467,0.0004544512,0.000001727578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005650608,"about_ca_system_score_gemma":0.0005696092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001587924,"about_ca_topic_score_gemma":0.002181065,"domain_scores_codex":[0.9948362,0.001903174,0.001150872,0.0002235715,0.0016011,0.0002851402],"domain_scores_gemma":[0.4766249,0.5220063,0.0004419196,0.0002693188,0.0005993835,0.00005819757],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008829656,0.0001963182,0.979346,0.00001552931,0.00001247153,0.000001162973,0.00132862,0.0003696717,0.002332287,0.001087397,0.0001919889,0.0142356],"study_design_scores_gemma":[0.0004569267,0.0001682996,0.9896991,0.0003171013,0.000005252279,0.0001026686,0.00115718,0.00160006,0.001054823,0.004512161,0.0008727582,0.00005370222],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.992271,0.001016081,0.00002489643,0.005898986,0.00008517859,0.0001586162,0.000001970397,1.32928e-7,0.0005431337],"genre_scores_gemma":[0.9929065,0.0001698147,0.006193594,0.0000128488,0.00007442362,0.000005856123,7.636751e-8,0.000004972829,0.0006318756],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5351517,"threshold_uncertainty_score":0.9071845,"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."}}