{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1192767,0.0005560616,0.0008549645,0.00225547,0.001342616,0.002131188,0.001546982,0.001288547,0.007147857],"category_scores_gemma":[0.2590904,0.0006312161,0.001793161,0.001136125,0.001269694,0.001926617,0.00225371,0.001347126,0.003990286],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001385562,"about_ca_system_score_gemma":0.002542703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001424569,"about_ca_topic_score_gemma":0.003479613,"domain_scores_codex":[0.8953744,0.05125715,0.01434673,0.005012402,0.032277,0.001732262],"domain_scores_gemma":[0.7374688,0.09612188,0.01640624,0.02471039,0.1225013,0.002791313],"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":[0.004427365,0.0027532,0.4018463,0.001731347,0.0006048843,0.0003325787,0.0173987,0.001067779,0.01551879,0.008783385,0.04311748,0.5024182],"study_design_scores_gemma":[0.001243184,0.007284304,0.7956979,0.002483778,0.0004637063,0.0009066815,0.006804225,0.01825346,0.03705427,0.004291367,0.1252089,0.0003081812],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"other","genre_scores_codex":[0.7447418,0.0008664142,0.1235413,0.004879438,0.001933017,0.05489584,0.005493552,0.0006210423,0.06302761],"genre_scores_gemma":[0.7347565,0.0002914963,0.1993897,0.001166822,0.0002501558,0.04662863,0.002825033,0.0003719431,0.01431983],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.1192767,"threshold_uncertainty_score":0.6308032,"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."}}