{"id":"W4413961213","doi":"10.1017/gmh.2025.10034.pr7","title":"Decision: Development and preliminary inter-rater reliability of the new PROOF tool to measure fidelity of problem-solving therapy for depression delivered by non-specialists in a low-resource African setting — R0/PR7","year":2025,"lang":"en","type":"peer-review","venue":"","topic":"Families in Therapy and Culture","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario","funders":"","keywords":"Fidelity; Reliability (semiconductor); Measure (data warehouse); Depression (economics); Inter-rater reliability; Proof of concept; Resource (disambiguation); Computer science; Psychology; Reliability engineering; Medicine; Data mining; Engineering; Rating scale; Developmental psychology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002150314,0.000581456,0.001183114,0.000112139,0.0001404676,0.00002949225,0.001060076,0.0006302153,0.0005704708],"category_scores_gemma":[0.0006019096,0.0003604362,0.0002901458,0.000488576,0.0001260038,0.00006932497,0.0005336411,0.0006004429,0.00000115163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001905675,"about_ca_system_score_gemma":0.0004399892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002617318,"about_ca_topic_score_gemma":0.0004314183,"domain_scores_codex":[0.9956904,0.0004505349,0.001744786,0.001103339,0.0005562853,0.0004546386],"domain_scores_gemma":[0.9967238,0.0006490356,0.0006817008,0.001268223,0.0005773387,0.0000998437],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001934773,0.0002797339,0.0002916718,0.002179162,0.000104515,8.048604e-7,0.00735417,0.00001698241,0.0001540898,0.000008529438,0.5906889,0.3969866],"study_design_scores_gemma":[0.002275154,0.0003915696,0.003439361,0.02121256,0.00007687783,0.000004367248,0.0008416612,0.00001941493,0.003606986,0.0004065766,0.9671478,0.0005777222],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"review","genre_gemma":"other","genre_scores_codex":[0.2552341,0.3732521,0.06322655,0.08631464,0.01172101,0.1075733,0.004202186,0.0003959295,0.09808008],"genre_scores_gemma":[0.2917915,0.007290137,0.1807724,0.04098785,0.001612563,0.01193928,0.002164837,0.000684769,0.4627567],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.3964089,"threshold_uncertainty_score":0.9998848,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01797533185359937,"score_gpt":0.3039958017645586,"score_spread":0.2860204699109593,"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."}}