{"id":"W4408181595","doi":"10.2196/69144","title":"Building and Beta-Testing Be Well Buddy Chatbot, a Secure, Credible and Trustworthy AI Chatbot That Will Not Misinform, Hallucinate or Stigmatize Substance Use Disorder: Development and Usability Study","year":2025,"lang":"en","type":"article","venue":"JMIR Human Factors","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Drug Abuse","keywords":"Preprint; Chatbot; Hallucinating; Trustworthiness; Psychology; Computer security; Computer science; Internet privacy; World Wide Web; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01590692,0.001010965,0.0005379741,0.0008731976,0.0007853908,0.001413166,0.001333864,0.001155198,0.004109621],"category_scores_gemma":[0.04123856,0.0006459574,0.0005713179,0.0002690386,0.001135489,0.002961232,0.001706626,0.001170669,0.001597956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008851282,"about_ca_system_score_gemma":0.001538872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001911512,"about_ca_topic_score_gemma":0.002784753,"domain_scores_codex":[0.9949392,0.003039452,0.0003834999,0.0006092613,0.0006819643,0.0003466889],"domain_scores_gemma":[0.9605387,0.02974869,0.0007769488,0.002330663,0.00505966,0.001545455],"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":[0.004215223,0.01188644,0.07282284,0.007133686,0.0003894048,0.004239353,0.08388973,0.0104476,0.09118859,0.007320508,0.05334377,0.6531229],"study_design_scores_gemma":[0.003622649,0.07351834,0.2172418,0.004415626,0.001199124,0.009503581,0.03937742,0.2162814,0.1319339,0.008193692,0.2934476,0.001264866],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9215927,0.0004663467,0.05662704,0.0005886523,0.0001961595,0.004453232,0.0006188303,0.007062454,0.008394549],"genre_scores_gemma":[0.8340521,0.0003689922,0.1462695,0.0008698587,0.00004470144,0.003828435,0.001491138,0.001542467,0.01153267],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01590692,"threshold_uncertainty_score":0.0841248,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2000447721943084,"score_gpt":0.4143608219852309,"score_spread":0.2143160497909224,"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."}}