{"id":"W2025715897","doi":"10.1177/1534508411430319","title":"Generalizability Theory Analysis of CBM Maze Reliability in Third- Through Fifth-Grade Students","year":2012,"lang":"en","type":"article","venue":"Assessment for Effective Intervention","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Generalizability theory; Psychology; Reliability (semiconductor); Statistics; Reliability engineering; Developmental psychology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03739825,0.0003893633,0.00061266,0.002709576,0.0005910532,0.001154335,0.0007981095,0.000730241,0.00233359],"category_scores_gemma":[0.1663046,0.0005021986,0.001374347,0.001018683,0.001791101,0.001207526,0.001595584,0.001196128,0.0002669959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00105592,"about_ca_system_score_gemma":0.0009343553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003668747,"about_ca_topic_score_gemma":0.003440032,"domain_scores_codex":[0.9854861,0.007214461,0.001076865,0.001884857,0.003888634,0.0004490671],"domain_scores_gemma":[0.753616,0.1909598,0.01622682,0.02065374,0.01688859,0.001655132],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005667064,0.0003831913,0.9546096,0.0001806074,0.0004499807,0.00008339793,0.005964699,0.001144453,0.001616337,0.001474452,0.0003241574,0.03320226],"study_design_scores_gemma":[0.00005045496,0.001436603,0.9860909,0.00008821962,0.0001791208,0.0001546371,0.002045552,0.005595107,0.001812689,0.001876607,0.0006464095,0.00002378476],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9880349,0.000228297,0.006213443,0.0001471592,0.0000229862,0.0002680286,0.0001235257,0.00004399968,0.004917675],"genre_scores_gemma":[0.9976191,0.00004935365,0.001921942,0.00002453522,0.000007462118,0.0001367271,0.00005993908,0.000008419092,0.0001724303],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03739825,"threshold_uncertainty_score":0.1977832,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1157747010120157,"score_gpt":0.4836803038693699,"score_spread":0.3679056028573542,"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."}}