{"id":"W107454019","doi":"10.55016/ojs/ajer.v49i1.54961","title":"An Investigation of the Accuracy of Alternative Methods of True Score Estimation in High-Stakes Mixed-Format Examinations","year":2003,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Statistics; Estimation; Psychology; Mathematics education; Econometrics; Mathematics; Engineering","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":[0.02350779,0.00008796576,0.0003410571,0.001671528,0.0001094722,0.00004431402,0.001112753,0.00006410314,0.0006649534],"category_scores_gemma":[0.6203342,0.00005554774,0.0001000416,0.004198945,0.0004229009,0.0008158581,0.00005896736,0.0003452587,0.000002410577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009332596,"about_ca_system_score_gemma":0.001176587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009477226,"about_ca_topic_score_gemma":0.0002236015,"domain_scores_codex":[0.9912435,0.004977012,0.001569457,0.0001764354,0.001844204,0.0001893538],"domain_scores_gemma":[0.6562556,0.3375832,0.002071387,0.0005025525,0.003475794,0.0001114706],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006151134,0.0003956578,0.8355836,0.00005057934,0.00004879669,1.300928e-7,0.0059292,0.006771742,0.01197729,0.1087941,0.0008664565,0.02952098],"study_design_scores_gemma":[0.0003033989,0.0001972831,0.7893562,0.0001473732,0.000009322251,0.00001506139,0.003176555,0.002141497,0.04007376,0.1644608,0.00006774023,0.00005093855],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9927331,0.0002135316,0.002943331,0.00128714,0.0004389652,0.0001758101,0.000005494282,2.249458e-7,0.002202383],"genre_scores_gemma":[0.928194,0.00003494177,0.07147182,0.00001191684,0.00003262157,0.000005964872,0.000002065622,0.000005435588,0.0002411933],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5968264,"threshold_uncertainty_score":0.8147379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6078835678103994,"score_gpt":0.5942529116662607,"score_spread":0.01363065614413872,"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."}}