{"id":"W2052069113","doi":"10.1111/emip.12003","title":"Validating Student Score Inferences With Person‐Fit Statistic and Verbal Reports: A Person‐Fit Study for Cognitive Diagnostic Assessment","year":2013,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Science Education and Pedagogy","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Statistic; Test (biology); Cognition; Consistency (knowledge bases); Psychology; Test statistic; Cognitive psychology; Artificial intelligence; Statistical hypothesis testing; Computer science; Statistics; Mathematics","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","sts"],"consensus_categories":[],"category_scores_codex":[0.004090074,0.0001697079,0.0001825724,0.00007908034,0.001315883,0.0008519161,0.0001140039,0.00003805379,0.0008568967],"category_scores_gemma":[0.01376665,0.0001435059,0.00001983706,0.0002046201,0.0002500664,0.001051542,0.00001994622,0.0001522427,0.00001128581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001817657,"about_ca_system_score_gemma":0.001495688,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008992793,"about_ca_topic_score_gemma":0.001966834,"domain_scores_codex":[0.9969896,0.0006644831,0.0002455241,0.0004827941,0.001320379,0.000297184],"domain_scores_gemma":[0.9918097,0.005891545,0.000350554,0.0001181215,0.001588743,0.0002413401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.00005651791,0.002100943,0.5686002,0.00005854704,0.0002447054,0.00000582631,0.4070252,0.000005210776,0.00002379614,0.006200463,0.00570953,0.009969058],"study_design_scores_gemma":[0.000293582,0.0004870402,0.3976256,0.00008424925,0.0001579607,0.00001548395,0.5949493,0.00001173883,0.000001571473,0.0003633191,0.00583843,0.000171739],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9348512,0.001481954,0.0004617436,0.0509715,0.001065921,0.003128484,0.00001433289,0.00003088097,0.007993989],"genre_scores_gemma":[0.9937828,0.0001406654,0.003191191,0.0004607043,0.0004871206,0.0009474742,0.00001246418,0.00001028355,0.0009672504],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1879241,"threshold_uncertainty_score":0.9999843,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3346735437565425,"score_gpt":0.504415793140177,"score_spread":0.1697422493836346,"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."}}