{"id":"W4409120023","doi":"10.2196/69534","title":"Is This Chatbot Safe and Evidence-Based? A Call for the Critical Evaluation of Generative AI Mental Health Chatbots","year":2025,"lang":"en","type":"article","venue":"Journal of Participatory Medicine","topic":"Digital Mental Health Interventions","field":"Psychology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Chatbot; Mental health; Psychology; Internet privacy; Computer science; Medicine; World Wide Web; Psychiatry","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":[0.005604678,0.0001190407,0.0003852404,0.0001740482,0.0001550537,0.00001028848,0.0001397887,0.00005291437,0.0006569659],"category_scores_gemma":[0.001386002,0.00007609796,0.0001130084,0.0001606522,0.0004218957,0.0001614464,0.00002343263,0.0001958847,0.000004502075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002318868,"about_ca_system_score_gemma":0.0004802363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008900803,"about_ca_topic_score_gemma":0.0000499708,"domain_scores_codex":[0.9973924,0.0005324202,0.001080929,0.0001571868,0.0005770242,0.0002601073],"domain_scores_gemma":[0.9974301,0.001145651,0.0004045174,0.0001911995,0.0006425335,0.0001859567],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.003465185,0.002473776,0.009575167,0.001989857,0.001157234,0.00001364496,0.03036601,0.00007978384,0.0009754811,0.04599077,0.7190824,0.1848307],"study_design_scores_gemma":[0.07023812,0.09421407,0.4043115,0.08803876,0.009192446,0.0005889656,0.02977599,0.1314498,0.02537067,0.04773026,0.0975832,0.001506125],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1950384,0.08341848,0.01107337,0.7019742,0.006109291,0.001693884,0.00006808602,0.000009960406,0.0006142473],"genre_scores_gemma":[0.9853751,0.00006233114,0.0001844898,0.01368534,0.0002407533,0.0001046625,0.00000148849,0.000008653877,0.0003371589],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7903367,"threshold_uncertainty_score":0.7193316,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3995995031340878,"score_gpt":0.5915934360208156,"score_spread":0.1919939328867278,"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."}}