{"id":"W4410110516","doi":"10.2196/68056","title":"Leveraging Large Language Models for Simulated Psychotherapy Client Interactions: Development and Usability Study of Client101","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Digital Mental Health Interventions","field":"Psychology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Usability; Computer science; Human–computer interaction; Psychology; World Wide Web","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004673662,0.00009563215,0.0001611034,0.0001551197,0.00008810217,0.00001494035,0.0001140531,0.00006399995,0.000337143],"category_scores_gemma":[0.00008043251,0.00009149551,0.00004122518,0.0001952741,0.00003545465,0.0001018522,0.0000228277,0.0001271941,0.000007807522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001179096,"about_ca_system_score_gemma":0.000267276,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009236666,"about_ca_topic_score_gemma":0.0001427074,"domain_scores_codex":[0.9986621,0.00009443037,0.0005809519,0.000293303,0.0001862769,0.0001829918],"domain_scores_gemma":[0.9992824,0.0001654641,0.0001202234,0.0002290176,0.00008681476,0.0001160635],"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":[0.000580074,0.0481874,0.01334549,0.0004621508,0.0002254651,8.309838e-7,0.09497569,0.00001415543,0.00001081268,0.01905718,0.006901183,0.8162396],"study_design_scores_gemma":[0.03047301,0.004073398,0.3862306,0.004604073,0.0001909531,0.00002238836,0.3473357,0.01701905,0.0006960877,0.05602961,0.1521055,0.001219669],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9890487,0.0002227348,0.003962663,0.001171518,0.001851476,0.001603477,0.00000669068,0.00003602651,0.002096682],"genre_scores_gemma":[0.9959277,0.000001793324,0.0003031841,0.0007649773,0.00003385414,0.0008453538,0.00003851593,0.000009268018,0.002075382],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8150199,"threshold_uncertainty_score":0.3731079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0420268087884928,"score_gpt":0.4859967225772346,"score_spread":0.4439699137887418,"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."}}