{"id":"W4414540359","doi":"10.1176/appi.psychotherapy.20250009","title":"How Patients Guide Therapy: A Pilot Study on the Development and Reliability of the Patient Coaching Rating System","year":2025,"lang":"en","type":"article","venue":"American Journal of Psychotherapy","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Coaching; Reliability (semiconductor); Rating system; Empirical research; Rating scale; Health coaching","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":[],"consensus_categories":[],"category_scores_codex":[0.001040008,0.0002045324,0.0003636991,0.0001174202,0.0002513105,0.00004998078,0.0005390206,0.00002436417,0.00001272598],"category_scores_gemma":[0.00001651024,0.0001056026,0.0001026733,0.0004981874,0.0002224214,0.00004288128,0.00001217163,0.0003115038,5.232068e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007131835,"about_ca_system_score_gemma":0.00006873986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006210087,"about_ca_topic_score_gemma":0.000009234162,"domain_scores_codex":[0.9977304,0.0007122643,0.0007650891,0.0002574019,0.0003426419,0.0001921669],"domain_scores_gemma":[0.9975249,0.0003571404,0.001171556,0.0006859915,0.0002135924,0.00004681646],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002672352,0.007365485,0.2453426,0.00001767502,0.0009186007,0.000001367463,0.03433516,0.000008562808,0.002444739,0.0112115,0.006461116,0.6892208],"study_design_scores_gemma":[0.006765358,0.02436794,0.7512344,0.0007331707,0.00007049697,0.00001717199,0.05904746,0.00001856717,0.002908084,0.001851036,0.1524263,0.000559999],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9863333,0.0001732959,0.006732411,0.003054089,0.0003799311,0.001087244,0.000004536388,0.00002200703,0.002213263],"genre_scores_gemma":[0.9964026,0.00006383131,0.001979175,0.001248196,0.00003541717,0.0001200326,2.02675e-7,0.00002325665,0.0001272852],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6886608,"threshold_uncertainty_score":0.4306349,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02408753431565867,"score_gpt":0.3263704811532301,"score_spread":0.3022829468375714,"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."}}