{"id":"W2139990047","doi":"10.1111/j.1745-3984.2011.00158.x","title":"Estimating Classification Consistency and Accuracy for Cognitive Diagnostic Assessment","year":2012,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":90,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Consistency (knowledge bases); Reliability (semiconductor); Computation; Subtraction; Statistical inference; Fraction (chemistry); Inference; Sampling (signal processing); Computer science; Statistics; Cognitive test; Artificial intelligence; Cognition; Mathematics; Data mining; Pattern recognition (psychology); Algorithm; Psychology; Arithmetic","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"],"consensus_categories":[],"category_scores_codex":[0.01755881,0.00009367985,0.0002330406,0.0003115727,0.0002003283,0.00012535,0.0001975389,0.00003293531,0.0001190171],"category_scores_gemma":[0.5315195,0.00006586008,0.00008713041,0.0003670149,0.00006919448,0.0004380513,0.00002605825,0.0001229945,0.000004801077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001528478,"about_ca_system_score_gemma":0.0004917271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001702537,"about_ca_topic_score_gemma":5.771904e-7,"domain_scores_codex":[0.9969359,0.0003369854,0.0009243715,0.0001474239,0.001463652,0.0001916889],"domain_scores_gemma":[0.8499768,0.1428482,0.002138834,0.0001841655,0.004572833,0.0002790968],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003328297,0.0004873956,0.7835364,0.000024465,0.00008520448,1.890232e-7,0.0004842632,0.00003324269,0.0009818539,0.007219022,0.006334284,0.2007804],"study_design_scores_gemma":[0.0004115498,0.0001155497,0.9614446,0.0001241555,0.00006172591,0.00004966875,0.001449265,0.0005093646,0.00006075354,0.03462409,0.001068881,0.00008043635],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5866523,0.006511315,0.377991,0.01699307,0.007250973,0.000722372,0.00001514055,0.000007064599,0.003856766],"genre_scores_gemma":[0.82965,0.00001558952,0.169406,0.00012705,0.0007489567,0.00002573635,0.000001017775,0.00000455033,0.00002108308],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5139607,"threshold_uncertainty_score":0.6085567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7019996993223337,"score_gpt":0.5564925005972196,"score_spread":0.1455071987251142,"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."}}