{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03522916,0.0001264905,0.0006549987,0.000241104,0.0003908334,0.0001259741,0.0006489491,0.00007528038,0.0007664826],"category_scores_gemma":[0.276087,0.0001032004,0.0001535407,0.0004838722,0.0003862845,0.0001176152,0.0002081888,0.0004804239,0.000004951632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003004739,"about_ca_system_score_gemma":0.00003440288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001867048,"about_ca_topic_score_gemma":3.976097e-7,"domain_scores_codex":[0.993342,0.003390525,0.001492911,0.0004355767,0.0009813923,0.0003575357],"domain_scores_gemma":[0.8488432,0.1499602,0.0004322104,0.0002394418,0.0003045209,0.0002204192],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.009728293,0.001916321,0.00103793,0.0000604491,0.00006645095,0.0005000552,0.0004195643,0.000590894,0.0002491807,0.2258634,0.02972569,0.7298418],"study_design_scores_gemma":[0.001555067,0.001125391,0.01857813,0.00001986251,0.00002108507,0.003260338,0.0006468656,0.01862223,9.072709e-7,0.9520822,0.003968183,0.0001197397],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2135176,0.0003832331,0.7843809,0.0003648262,0.0004600329,0.0001911009,0.0002330067,0.00001088875,0.0004583873],"genre_scores_gemma":[0.8021678,0.00002007177,0.1970024,0.0005429733,0.00005502924,0.00002136333,0.000002008625,0.00001287623,0.0001755064],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.729722,"threshold_uncertainty_score":0.9934346,"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."}}