{"id":"W4413961328","doi":"10.1017/gmh.2025.10034.pr5","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 — R0/PR5","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); Inter-rater reliability; Reliability (semiconductor); Depression (economics); Proof of concept; Resource (disambiguation); 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":[0.09340704,0.0008404808,0.003612569,0.01091191,0.001065474,0.003590014,0.002143146,0.001493185,0.002530741],"category_scores_gemma":[0.3193726,0.0009376545,0.003768587,0.01020315,0.001253487,0.002216262,0.001748071,0.001208243,0.0007575358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004928613,"about_ca_system_score_gemma":0.01798857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005776222,"about_ca_topic_score_gemma":0.02181652,"domain_scores_codex":[0.869001,0.06156635,0.0361296,0.002202345,0.03036058,0.0007401138],"domain_scores_gemma":[0.6458982,0.2043911,0.04370776,0.009721685,0.09465556,0.001625708],"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":[0.0009050848,0.00009989187,0.01021288,0.440345,0.008934289,0.0003670881,0.002495178,0.0003607188,0.001471006,0.00160928,0.0193933,0.5138062],"study_design_scores_gemma":[0.001167088,0.001773632,0.0914479,0.614194,0.03508085,0.001814634,0.001587914,0.001543158,0.002768478,0.001635925,0.2466813,0.0003051353],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"other","genre_scores_codex":[0.02784372,0.8895558,0.02139556,0.009290654,0.002538606,0.02971056,0.006421397,0.0002367375,0.01300698],"genre_scores_gemma":[0.1927113,0.6795279,0.07524545,0.003343523,0.0007680796,0.04058514,0.004577248,0.0001482663,0.003093143],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.09340704,"threshold_uncertainty_score":0.4939896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07201903900394914,"score_gpt":0.4065296812950697,"score_spread":0.3345106422911206,"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."}}