{"id":"W4413961208","doi":"10.1017/gmh.2025.10034.pr6","title":"Recommendation: 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/PR6","year":2025,"lang":"en","type":"peer-review","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario","funders":"","keywords":"Fidelity; Measure (data warehouse); Reliability (semiconductor); Depression (economics); Proof of concept; Resource (disambiguation); Inter-rater reliability; Computer science; Psychology; Clinical psychology; Data mining; Developmental psychology; Rating scale","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":[0.1412417,0.000895765,0.001207222,0.002919201,0.001818626,0.002982605,0.003237849,0.005028707,0.02754032],"category_scores_gemma":[0.4948699,0.0008510607,0.002940297,0.003330106,0.001647517,0.003401768,0.002215612,0.002990879,0.02080272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003929832,"about_ca_system_score_gemma":0.01481581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01079485,"about_ca_topic_score_gemma":0.02236632,"domain_scores_codex":[0.8610453,0.06400577,0.02239198,0.003297821,0.04705641,0.002202751],"domain_scores_gemma":[0.453236,0.1720241,0.02956608,0.04119314,0.2963956,0.007584997],"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":[0.0019172,0.001834476,0.05894543,0.005984674,0.0005195156,0.00009836876,0.001908245,0.0004110356,0.001764881,0.002270226,0.5052381,0.4191079],"study_design_scores_gemma":[0.006276857,0.004333707,0.4252427,0.02266997,0.001252051,0.0004275512,0.003712676,0.006863941,0.01114838,0.004762992,0.5128495,0.0004595708],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"protocol","genre_gemma":"other","genre_scores_codex":[0.1360522,0.003773505,0.1065097,0.1115164,0.009844237,0.2808656,0.1044378,0.004450369,0.2425503],"genre_scores_gemma":[0.2342906,0.002027536,0.456412,0.02323837,0.001123673,0.2115898,0.02420349,0.001281666,0.04583301],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.1412417,"threshold_uncertainty_score":0.7469665,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08079934618591844,"score_gpt":0.4076446152055804,"score_spread":0.3268452690196619,"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."}}