{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001121402,0.0002406485,0.0006240542,0.0006793007,0.00007911858,0.00001683499,0.0005789534,0.0002994771,0.0002678556],"category_scores_gemma":[0.000004758476,0.0002142058,0.0001017656,0.0005252513,0.0001875101,0.000278078,0.00001518381,0.0007501218,0.000004284133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001259953,"about_ca_system_score_gemma":0.00003934918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001656516,"about_ca_topic_score_gemma":0.0002783994,"domain_scores_codex":[0.9975311,0.0005286584,0.0009917492,0.0004587186,0.0001496541,0.0003401723],"domain_scores_gemma":[0.9984472,0.00007921662,0.0004766701,0.0007283617,0.0001610683,0.0001074754],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.01137757,0.06115061,0.1056089,0.00008657369,0.001871925,0.0005414116,0.1399038,0.00004368861,0.05323049,0.2553237,0.1668459,0.2040154],"study_design_scores_gemma":[0.05692928,0.01458505,0.4871376,0.000568535,0.0002365699,0.0005964015,0.02340602,0.0001992031,0.000433903,0.2981025,0.1164902,0.001314653],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9587961,0.006745323,0.01877356,0.009227236,0.0009271919,0.0005819273,0.00002007468,0.00004399017,0.004884603],"genre_scores_gemma":[0.9774799,0.001212224,0.0006548977,0.02033669,0.00008625125,0.00006864174,0.000002023057,0.00002528075,0.0001340851],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3815287,"threshold_uncertainty_score":0.8735059,"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."}}