{"id":"W4413773148","doi":"10.1080/29974100.2025.2545258","title":"AI meets psychology: an exploratory study of large language models’ competence in psychotherapy contexts","year":2025,"lang":"en","type":"article","venue":"Journal of Psychology and AI","topic":"Psychotherapy Techniques and Applications","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Child, Adolescent and Family Mental Health","funders":"","keywords":"Psychology; Psychotherapist; Competence (human resources); Exploratory research; Cognitive science; Social psychology; Sociology; Social science","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":[0.01438435,0.000436531,0.0004666118,0.001484317,0.002821341,0.004223243,0.00133226,0.001205502,0.00219214],"category_scores_gemma":[0.03626776,0.0006416894,0.0003335893,0.0008678318,0.003343652,0.003547058,0.005146992,0.002071929,0.000383867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002802873,"about_ca_system_score_gemma":0.003782246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002078082,"about_ca_topic_score_gemma":0.003968785,"domain_scores_codex":[0.9864963,0.01109386,0.0003287853,0.0005617458,0.0008644068,0.0006549654],"domain_scores_gemma":[0.9680159,0.0259911,0.001823887,0.001551935,0.001118407,0.001498813],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0002060346,0.002338769,0.04449218,0.0002818418,0.00002016169,0.0008016272,0.9062355,0.0006112998,0.002953735,0.00356012,0.0006531721,0.03784555],"study_design_scores_gemma":[0.0001322098,0.002484939,0.0602647,0.0003626794,0.00004800608,0.001367248,0.8959965,0.007326518,0.004017437,0.007194237,0.02069479,0.0001107245],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9942454,0.00006742203,0.00296235,0.000297068,0.00000370169,0.0002736923,0.00002542789,0.0000190989,0.002105884],"genre_scores_gemma":[0.9923688,0.00009758137,0.006252857,0.0001457451,0.000004092683,0.0004543554,0.00003824875,0.00001945248,0.0006188974],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01438435,"threshold_uncertainty_score":0.07607257,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03333696749225484,"score_gpt":0.4432401068165597,"score_spread":0.4099031393243048,"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."}}