{"id":"W4413961006","doi":"10.1017/gmh.2025.10034.pr9","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 — R1/PR9","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; Psychology; Computer science; 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":[0.08978117,0.0008347351,0.003551905,0.01062766,0.001055969,0.003540728,0.002104468,0.001485204,0.002510993],"category_scores_gemma":[0.3134044,0.0009305434,0.00371241,0.009922275,0.001232245,0.00217639,0.001703313,0.001192887,0.0007515899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004831393,"about_ca_system_score_gemma":0.01796845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00573304,"about_ca_topic_score_gemma":0.02178423,"domain_scores_codex":[0.874007,0.05938343,0.03457254,0.00209937,0.02921904,0.0007186063],"domain_scores_gemma":[0.65455,0.2003105,0.04286685,0.009478522,0.09120513,0.001588983],"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":[0.0008956829,0.0001009165,0.009849264,0.4423942,0.008892556,0.0003648501,0.002432459,0.000350394,0.001488447,0.001552743,0.01940443,0.5122741],"study_design_scores_gemma":[0.001162529,0.001775929,0.08875816,0.6204758,0.03505497,0.001779209,0.001563855,0.001488395,0.002764488,0.001573137,0.2433074,0.0002961699],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"other","genre_scores_codex":[0.02784283,0.8917547,0.02037299,0.009326783,0.002527245,0.02897401,0.006203569,0.0002296206,0.01276822],"genre_scores_gemma":[0.1884441,0.6899009,0.07148336,0.003334126,0.0007609048,0.03859579,0.004312486,0.0001437199,0.003024697],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.08978117,"threshold_uncertainty_score":0.4748139,"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."}}