{"id":"W4408051986","doi":"10.1016/j.bjpt.2025.101193","title":"Considerations when designing, analyzing, and reporting reliability studies","year":2025,"lang":"en","type":"review","venue":"Brazilian Journal of Physical Therapy","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Reliability (semiconductor); Reliability engineering; Computer science; Engineering; Physics; Thermodynamics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01739642,0.0004816853,0.00404064,0.0004447107,0.0003582154,0.0004162945,0.0006755179,0.0001476743,0.00008881078],"category_scores_gemma":[0.0432203,0.0002653702,0.001632951,0.0006324901,0.0004117403,0.0003824211,0.0001450698,0.0007928662,0.00001220034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001429331,"about_ca_system_score_gemma":0.0008049056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001917603,"about_ca_topic_score_gemma":0.000001839747,"domain_scores_codex":[0.9897808,0.002093944,0.005372491,0.000681052,0.00177564,0.0002960728],"domain_scores_gemma":[0.9770721,0.01120569,0.008688362,0.0009073329,0.001920748,0.0002057833],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001493955,0.0002147225,0.0001856284,0.001039597,0.0005393818,0.00002971816,0.0008430255,0.00002247924,0.000009784755,0.0003807589,0.009175063,0.9875449],"study_design_scores_gemma":[0.0003951806,0.0004884191,0.00007154773,0.01034208,0.000510934,0.00006126914,0.0003059107,0.000008146957,0.00004352868,0.2865545,0.700856,0.0003625242],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000548862,0.9969512,0.0004111651,0.000641087,0.0004667455,0.0006020279,0.000008625792,0.00001333048,0.0003569544],"genre_scores_gemma":[0.0007275427,0.9956597,0.002580166,0.000121442,0.0005095156,0.00001761086,9.058311e-7,0.00001597002,0.0003671479],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9871824,"threshold_uncertainty_score":0.9999799,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3977318700523943,"score_gpt":0.5038276533868976,"score_spread":0.1060957833345033,"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."}}