{"id":"W4414049566","doi":"10.1017/gmh.2025.10034","title":"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","year":2025,"lang":"en","type":"article","venue":"Cambridge Prisms Global Mental Health","topic":"Problem Solving Skills Development","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Fidelity; Competence (human resources); Proof of concept; Reliability (semiconductor); Psychometrics; Measure (data warehouse)","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002388972,0.0003333287,0.0006456155,0.00009072782,0.0005429203,0.00001362526,0.000486396,0.0001968123,0.000005001627],"category_scores_gemma":[0.0003486184,0.0002575679,0.00008153602,0.0005679392,0.00008461563,0.0001151814,0.000863887,0.0003678007,0.000001122892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002446427,"about_ca_system_score_gemma":0.002810023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001338029,"about_ca_topic_score_gemma":0.0005026229,"domain_scores_codex":[0.99569,0.0005611091,0.001817361,0.0007018608,0.0004380858,0.0007915063],"domain_scores_gemma":[0.9980435,0.0002377048,0.000726575,0.0005243564,0.0002423646,0.0002254979],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.004611909,0.00106586,0.4456284,0.006592948,0.00009786181,9.745415e-7,0.03668814,0.00005564231,0.003352769,0.0001946345,0.1182487,0.3834621],"study_design_scores_gemma":[0.007262863,0.0005628101,0.9322768,0.01827285,0.00001831213,0.000002557776,0.003327509,0.0004336807,0.0155595,0.000353713,0.0213329,0.0005964847],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9725656,0.001279227,0.007505754,0.006327981,0.0003704061,0.01116649,0.0002584845,0.00004091876,0.0004851528],"genre_scores_gemma":[0.9624401,0.00003937754,0.03433782,0.002253989,0.0000280571,0.0005415816,0.00005487965,0.00002461699,0.0002795296],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4866484,"threshold_uncertainty_score":0.9999877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0144471478824518,"score_gpt":0.3255608023549252,"score_spread":0.3111136544724734,"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."}}