{"id":"W2329561122","doi":"10.4995/head15.2015.364","title":"Mixed-format exams in higher education: Assessment of internal consistency reliability","year":2015,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Reliability (semiconductor); Internal consistency; Measure (data warehouse); Consistency (knowledge bases); Computer science; Multiple choice; Reproducibility; Mathematics education; Test (biology); Psychology; Statistics; Mathematics; Significant difference; Psychometrics; Artificial intelligence; Data mining","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":[],"category_scores_codex":[0.01072877,0.00008180676,0.0002837961,0.0003454412,0.00002060512,0.00005895436,0.0005634594,0.00005312925,0.001161704],"category_scores_gemma":[0.02627532,0.00005143206,0.00006057116,0.001381287,0.000093674,0.0002437972,0.0001803275,0.000123167,0.00002497432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008676514,"about_ca_system_score_gemma":0.0002802693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003056858,"about_ca_topic_score_gemma":0.00001696217,"domain_scores_codex":[0.9973218,0.0004713303,0.0009038846,0.0002864037,0.000862712,0.0001539037],"domain_scores_gemma":[0.9904612,0.008015019,0.0003170557,0.0006166985,0.0004662407,0.0001237703],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000007993032,0.0001423965,0.8760645,0.000004244052,0.000002396508,6.148958e-7,0.00007333281,0.00003709463,0.00001211824,0.008427791,0.02375983,0.09146765],"study_design_scores_gemma":[0.0002771879,0.00008300789,0.9066481,0.00001672826,0.000002010512,0.000005278683,0.002002694,0.0006375136,0.00006281462,0.06751005,0.02267858,0.00007602051],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5947873,0.0001321824,0.004691888,0.001201438,0.002731567,0.00009814505,0.000001229952,0.00001927255,0.396337],"genre_scores_gemma":[0.9109786,0.000002740844,0.08480059,0.0003325975,0.00004824125,0.000007165039,4.4911e-7,0.000002552923,0.003827126],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3925098,"threshold_uncertainty_score":0.9997514,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7094676573679086,"score_gpt":0.5307209581113188,"score_spread":0.1787466992565898,"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."}}