{"id":"W4214686438","doi":"10.1111/bmsp.12269","title":"Reliability coefficients for multiple group item response theory models","year":2022,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reliability (semiconductor); Item response theory; Group (periodic table); Mathematics; Statistics; Econometrics; Reliability engineering; Psychology; Psychometrics; Engineering; Physics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.07864314,0.001993677,0.002107329,0.006427801,0.0008077191,0.003256665,0.003379025,0.002729947,0.008009175],"category_scores_gemma":[0.3555239,0.001406034,0.003830394,0.007744401,0.002575793,0.00524166,0.002568186,0.005468875,0.004096461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002006543,"about_ca_system_score_gemma":0.001715448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002282486,"about_ca_topic_score_gemma":0.001980549,"domain_scores_codex":[0.9263778,0.05440829,0.003183649,0.005249509,0.009955405,0.000825277],"domain_scores_gemma":[0.7610295,0.1890119,0.01081469,0.02080178,0.01779338,0.0005487977],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002800782,0.0002486742,0.04228684,0.001987909,0.001392983,0.0003667859,0.004868264,0.1233937,0.001418996,0.4627885,0.0295831,0.3313841],"study_design_scores_gemma":[0.0001505334,0.0004705007,0.030146,0.001968769,0.0006649743,0.0009153222,0.001252568,0.3325509,0.001370919,0.5907818,0.03935513,0.0003725745],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009707831,0.0007768097,0.9838789,0.0004784287,0.0001469976,0.0004798919,0.0008146158,0.0005211448,0.003195492],"genre_scores_gemma":[0.246539,0.001570525,0.7384889,0.0004507006,0.0003392499,0.006081187,0.002663285,0.0009092923,0.002957852],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07864314,"threshold_uncertainty_score":0.4159096,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3057821453871747,"score_gpt":0.4634622157514617,"score_spread":0.157680070364287,"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."}}