{"id":"W4413961331","doi":"10.1017/gmh.2025.10034.pr2","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/PR2","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); Proof of concept; Inter-rater reliability; Reliability (semiconductor); Depression (economics); Resource (disambiguation); Computer science; Psychology; Medicine; Data mining; 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":[0.09109484,0.0008571212,0.003675373,0.0108866,0.001074778,0.003595983,0.00214453,0.001516429,0.002462756],"category_scores_gemma":[0.3128207,0.0009421123,0.003744401,0.01034897,0.001256712,0.002216551,0.001728522,0.001206946,0.000745589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004936222,"about_ca_system_score_gemma":0.01789038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005766143,"about_ca_topic_score_gemma":0.02184939,"domain_scores_codex":[0.8736516,0.05967714,0.0349006,0.002129705,0.02892087,0.0007199855],"domain_scores_gemma":[0.6527928,0.1998736,0.04333372,0.009487594,0.09287307,0.001639212],"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":[0.0009074914,0.0001000645,0.009863811,0.4526441,0.008871689,0.0003736223,0.002487533,0.0003490023,0.001476245,0.001541966,0.01902153,0.5023629],"study_design_scores_gemma":[0.001169005,0.001783469,0.08967152,0.6215079,0.03562343,0.001838781,0.001604165,0.001501213,0.002732076,0.001565192,0.2407043,0.0002988893],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"other","genre_scores_codex":[0.02711656,0.8948568,0.01974792,0.009049733,0.002468435,0.02843158,0.00597978,0.0002228049,0.01212642],"genre_scores_gemma":[0.1858194,0.6925329,0.07098854,0.003307896,0.0007503566,0.0391836,0.004319759,0.0001403035,0.002957281],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.09109484,"threshold_uncertainty_score":0.4817613,"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."}}