{"id":"W4413961343","doi":"10.1017/gmh.2025.10034.pr12","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 — R1/PR12","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); Depression (economics); Reliability (semiconductor); Inter-rater reliability; Proof of concept; Resource (disambiguation); Computer science; 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":[0.1193489,0.0005632752,0.0008327243,0.002526154,0.001081175,0.002023071,0.001208059,0.0008741624,0.00457297],"category_scores_gemma":[0.2523573,0.0005872438,0.001847669,0.001499921,0.00119643,0.001680874,0.002273902,0.001120572,0.002020842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001466519,"about_ca_system_score_gemma":0.002468314,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001539813,"about_ca_topic_score_gemma":0.003794899,"domain_scores_codex":[0.8763513,0.06375508,0.0175734,0.0050939,0.03539349,0.0018328],"domain_scores_gemma":[0.7372178,0.1190338,0.02200329,0.02013393,0.09940676,0.00220439],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00354624,0.002249326,0.4768617,0.001426092,0.000620477,0.000205826,0.01619367,0.001508918,0.009395902,0.006097522,0.02097176,0.4609225],"study_design_scores_gemma":[0.0009254673,0.005619808,0.8674694,0.001448173,0.0004515073,0.0005820973,0.005771828,0.02251771,0.02675426,0.003148794,0.06506351,0.0002473873],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"other","genre_scores_codex":[0.8038647,0.0006376554,0.1142182,0.001908645,0.0008029317,0.0351938,0.004311427,0.0004716344,0.03859106],"genre_scores_gemma":[0.7719494,0.0002560675,0.1829628,0.000406955,0.0001440171,0.03235254,0.002654507,0.000243194,0.009030529],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.1193489,"threshold_uncertainty_score":0.6311847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06682207619746232,"score_gpt":0.4018516209327718,"score_spread":0.3350295447353095,"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."}}