{"id":"W4413960996","doi":"10.1017/gmh.2025.10034.pr10","title":"Review: 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 — R1/PR10","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); Inter-rater reliability; Resource (disambiguation); Psychology; Proof of concept; Computer science; Medicine; Data mining; Rating scale; Developmental psychology; Telecommunications; Computer network","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":[0.08495256,0.0008421081,0.003440062,0.01040822,0.001041285,0.00344874,0.002095663,0.001484587,0.00271903],"category_scores_gemma":[0.2967518,0.0009146181,0.003566748,0.009846708,0.001230113,0.002156602,0.001671774,0.001207833,0.0008123612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004938789,"about_ca_system_score_gemma":0.01875499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005882792,"about_ca_topic_score_gemma":0.02227767,"domain_scores_codex":[0.8818333,0.05576568,0.03175385,0.002030734,0.02791679,0.0006996865],"domain_scores_gemma":[0.670497,0.1880043,0.04125845,0.008992298,0.08963301,0.001614965],"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":[0.0008489902,0.00009409754,0.008318553,0.4495656,0.007934119,0.0003526833,0.002230526,0.000332777,0.001467814,0.001546754,0.02160128,0.5057068],"study_design_scores_gemma":[0.001067913,0.001603339,0.07555471,0.6222087,0.03128906,0.001686007,0.001377069,0.001298469,0.002675864,0.001522647,0.2594447,0.0002715398],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"other","genre_scores_codex":[0.02347161,0.8986655,0.01922456,0.009959299,0.002475597,0.02715407,0.006195873,0.0002252704,0.01262818],"genre_scores_gemma":[0.1641089,0.7212811,0.06628948,0.003483735,0.000754579,0.03647975,0.004260537,0.0001434484,0.003198509],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.08495256,"threshold_uncertainty_score":0.4492774,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07120928461470935,"score_gpt":0.4063434795554308,"score_spread":0.3351341949407215,"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."}}