{"id":"W2468688964","doi":"10.1177/2158244016653791","title":"Differential Performance on National Exams","year":2016,"lang":"en","type":"article","venue":"SAGE Open","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Differential item functioning; Test (biology); Psychology; Certificate; Item response theory; Subject (documents); Social psychology; Psychometrics; Clinical psychology; Mathematics; Computer science","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":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002987803,0.00007195434,0.0001445331,0.0001698739,0.0001354302,0.0002605676,0.001393585,0.00003393065,0.005724616],"category_scores_gemma":[0.02720366,0.00003380424,0.00003661817,0.0005554705,0.00004166161,0.0003170511,0.0004025427,0.00005333638,0.001067671],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002673109,"about_ca_system_score_gemma":0.00003491933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006596218,"about_ca_topic_score_gemma":0.000002194938,"domain_scores_codex":[0.998104,0.0001877535,0.0002600303,0.0003266938,0.0009530457,0.0001684543],"domain_scores_gemma":[0.9893924,0.01001332,0.0001260771,0.0003211899,0.00009106365,0.00005597211],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00003140137,0.00002047492,0.02898327,4.035139e-7,0.000003580097,0.0000010072,0.00002007061,0.000001983965,0.0008732841,0.001150541,0.006330232,0.9625837],"study_design_scores_gemma":[0.0008574148,0.0001735132,0.9112151,0.00005847009,0.000001739518,0.000004402106,0.00004161447,0.0001880808,0.003043137,0.04114836,0.04310937,0.0001587489],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7385551,0.0000109294,0.008434835,0.0007575629,0.0007176882,0.0001442385,0.00001034631,0.00002049531,0.2513488],"genre_scores_gemma":[0.9784322,0.00001239653,0.002318331,0.000231781,0.0001345624,0.000006945349,4.593865e-7,0.000004445094,0.01885885],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.962425,"threshold_uncertainty_score":0.9997101,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6708101331326844,"score_gpt":0.5210443421341487,"score_spread":0.1497657909985357,"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."}}