{"id":"W4413961330","doi":"10.1017/gmh.2025.10034.pr4","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/PR4","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); Psychology; Computer science; Medicine; Clinical psychology; 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":[0.08704618,0.0008572772,0.003574712,0.01076062,0.001064099,0.003558153,0.002131766,0.001529215,0.002593162],"category_scores_gemma":[0.3021831,0.0009324179,0.003652417,0.01013613,0.001264677,0.002215149,0.001702147,0.001216022,0.0007844308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004986283,"about_ca_system_score_gemma":0.01850527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005932256,"about_ca_topic_score_gemma":0.02216631,"domain_scores_codex":[0.8791043,0.05698988,0.03286322,0.002079544,0.02825659,0.0007065225],"domain_scores_gemma":[0.6627283,0.1938415,0.04186822,0.009215727,0.09072623,0.001620059],"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":[0.0008583012,0.00009421996,0.008799764,0.4529126,0.008383416,0.0003649196,0.002280021,0.0003394143,0.001456189,0.001569004,0.02025338,0.5026887],"study_design_scores_gemma":[0.001072677,0.001624891,0.07802547,0.6275529,0.03348374,0.001741059,0.001438115,0.001369539,0.00266873,0.001550737,0.2491937,0.000278428],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"other","genre_scores_codex":[0.02338741,0.9031541,0.01862005,0.009282346,0.002413821,0.02539649,0.005722343,0.0002151874,0.01180828],"genre_scores_gemma":[0.1681885,0.7207322,0.06459734,0.003377873,0.0007385295,0.03510639,0.004100833,0.0001384684,0.003019835],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.08704618,"threshold_uncertainty_score":0.4603497,"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."}}