{"id":"W4413961005","doi":"10.1017/gmh.2025.10034.pr11","title":"Recommendation: 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/PR11","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; Inter-rater reliability; Measure (data warehouse); Depression (economics); Reliability (semiconductor); Resource (disambiguation); Proof of concept; Computer science; Psychology; Medicine; Data mining; Developmental psychology; Rating scale; Computer network; Telecommunications; Operating system","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":[0.1404475,0.0009012067,0.001218123,0.002870419,0.001825604,0.002987809,0.00322598,0.004870016,0.02794757],"category_scores_gemma":[0.4962381,0.0008551564,0.002901179,0.003286788,0.001635718,0.003390009,0.002188015,0.002997032,0.02081761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004034964,"about_ca_system_score_gemma":0.01506761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01104413,"about_ca_topic_score_gemma":0.02331473,"domain_scores_codex":[0.859954,0.0642499,0.02208523,0.003359986,0.04810522,0.002245693],"domain_scores_gemma":[0.4540628,0.1703365,0.03016179,0.0418903,0.2961124,0.007436234],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001825207,0.00177936,0.05793315,0.005756028,0.0005023236,0.00009716789,0.001930512,0.000398692,0.001683264,0.002214338,0.5115113,0.4143685],"study_design_scores_gemma":[0.006247199,0.004248308,0.4230055,0.02216119,0.00122529,0.0004295982,0.003733305,0.006878571,0.01106776,0.004713475,0.5158309,0.0004589673],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"protocol","genre_gemma":"other","genre_scores_codex":[0.1353235,0.003719313,0.1059927,0.1125166,0.009570539,0.2832326,0.103114,0.004448703,0.2420823],"genre_scores_gemma":[0.2355137,0.002030938,0.4497695,0.02359392,0.001110887,0.2166314,0.02404827,0.001328074,0.0459734],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.1404475,"threshold_uncertainty_score":0.7427663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08165580773228148,"score_gpt":0.4071247314732017,"score_spread":0.3254689237409202,"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."}}