{"id":"W2736540189","doi":"10.7160/eriesj.2017.100202","title":"BAYESIAN DIAGNOSTICS FOR TEST DESIGN AND ANALYSIS","year":2017,"lang":"en","type":"article","venue":"Journal on Efficiency and Responsibility in Education and Science","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; AXYS Technologies (Canada)","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bayesian probability; Computer science; Bayesian statistics; Test (biology); Bridge (graph theory); Item response theory; Bayesian experimental design; Artificial intelligence; Machine learning; Posterior probability; Test theory; Bayesian inference; Econometrics; Natural language processing; Statistics; Mathematics; Psychometrics","routes":{"ca_aff":true,"ca_fund":true,"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","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03380434,0.0001026531,0.0002600001,0.001408242,0.002052019,0.001479751,0.000617711,0.00005211987,0.00001008053],"category_scores_gemma":[0.4033822,0.00006555505,0.00004708076,0.001759464,0.001069167,0.0004393529,0.00009995035,0.0001823243,5.658845e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004163815,"about_ca_system_score_gemma":0.0005123317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001023479,"about_ca_topic_score_gemma":0.000007130334,"domain_scores_codex":[0.9977096,0.0003425419,0.000510469,0.0005587566,0.0006169323,0.000261745],"domain_scores_gemma":[0.9495715,0.04845548,0.0005341702,0.0006400634,0.0004809778,0.000317739],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008969965,0.0003334896,0.7095187,0.000004425306,0.000004072105,0.000001822941,0.0009254692,0.0003538971,0.0002381026,0.00108111,0.0001110272,0.2873382],"study_design_scores_gemma":[0.0002028287,0.0002899378,0.9247082,0.00001990856,0.00001511993,0.00003096392,0.0009935262,0.04429124,0.0000552482,0.02897337,0.0003279596,0.00009168788],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9032068,0.0005676075,0.09241574,0.002633792,0.0005849242,0.0002093539,0.000003152999,0.000004547271,0.0003741382],"genre_scores_gemma":[0.9716691,0.0003787026,0.0275456,0.000191323,0.0000414726,0.000005122934,7.896925e-8,0.000001908034,0.0001666734],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3695778,"threshold_uncertainty_score":0.9995568,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2680513155235794,"score_gpt":0.5076812887630598,"score_spread":0.2396299732394805,"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."}}