{"id":"W2118357141","doi":"10.22230/ijepl.2008v3n6a106","title":"Testing the Testing: Validity of a State Growth Model","year":2008,"lang":"en","type":"article","venue":"International Journal of Education Policy and Leadership","topic":"School Choice and Performance","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"State (computer science); Variance (accounting); Predictive power; Econometrics; Regression analysis; Accountability; Power (physics); Statistics; Generalized estimating equation; Mathematics; Political science; Economics; Law; Accounting; Physics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05204551,0.0007918888,0.001207192,0.00158256,0.001720082,0.003776421,0.004131676,0.001220651,0.004088837],"category_scores_gemma":[0.2011065,0.0005571837,0.001349407,0.002174955,0.003282261,0.003944256,0.002972419,0.00335086,0.0004775419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002872466,"about_ca_system_score_gemma":0.006299697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.05919754,"about_ca_topic_score_gemma":0.03174672,"domain_scores_codex":[0.9674895,0.02237471,0.001178022,0.003882125,0.003916688,0.001158952],"domain_scores_gemma":[0.640192,0.3061042,0.01136537,0.02101663,0.019743,0.001578857],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001103491,0.0008330166,0.7945314,0.0002282292,0.001118305,0.0005384947,0.006311785,0.07555868,0.0005885052,0.07224324,0.005283128,0.04166168],"study_design_scores_gemma":[0.0002124813,0.0007478743,0.2142778,0.0002551719,0.0005032078,0.0002107397,0.003736488,0.7248257,0.001453371,0.04595834,0.007708635,0.0001102268],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9164053,0.000113839,0.05504677,0.004327695,0.0001697775,0.0004021769,0.001449782,0.0002391832,0.02184555],"genre_scores_gemma":[0.9913703,0.0000273259,0.007015053,0.0001649159,0.0000296895,0.0001658255,0.0004781367,0.00002398921,0.000724661],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05919754,"threshold_uncertainty_score":0.2752463,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.456486840491535,"score_gpt":0.418599088773189,"score_spread":0.03788775171834607,"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."}}