{"id":"W4413961329","doi":"10.1017/gmh.2025.10034.pr3","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/PR3","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":[0.08973581,0.000845055,0.003547147,0.01070109,0.001057315,0.003533938,0.002110781,0.001493284,0.002535673],"category_scores_gemma":[0.3100801,0.0009306986,0.00365454,0.01012808,0.00124251,0.002186748,0.001701018,0.001191499,0.0007692614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004899534,"about_ca_system_score_gemma":0.01823305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005800467,"about_ca_topic_score_gemma":0.02181212,"domain_scores_codex":[0.8751512,0.05874399,0.0341933,0.002112085,0.02907929,0.0007202247],"domain_scores_gemma":[0.6543658,0.1977375,0.04287386,0.009423656,0.09396904,0.00163026],"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":[0.0009052159,0.00009953325,0.009713928,0.4413257,0.008506945,0.0003699065,0.002417475,0.0003482414,0.001508428,0.001561691,0.020047,0.513196],"study_design_scores_gemma":[0.001142754,0.001764246,0.0877337,0.6164511,0.03411803,0.001808678,0.001533283,0.001482066,0.002843707,0.001580382,0.2492484,0.0002935272],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"other","genre_scores_codex":[0.02671354,0.8943399,0.02007436,0.009506783,0.00248788,0.02793375,0.006178746,0.0002265814,0.01253852],"genre_scores_gemma":[0.1842529,0.6963968,0.06951242,0.003364312,0.0007634935,0.03809621,0.004359872,0.0001437098,0.003110314],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.08973581,"threshold_uncertainty_score":0.474574,"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."}}