{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005826426,0.000350185,0.0005323621,0.0002666475,0.0007382527,0.0002067343,0.00009997854,0.0001474175,0.00004592866],"category_scores_gemma":[0.0003001138,0.0002801963,0.00003452205,0.0003873495,0.0002042426,0.0006050913,0.00009784749,0.0003581836,0.000001108263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001535694,"about_ca_system_score_gemma":0.0002065195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001539775,"about_ca_topic_score_gemma":0.004298048,"domain_scores_codex":[0.9978018,0.00006899488,0.0006964806,0.0006237218,0.0003489949,0.0004599776],"domain_scores_gemma":[0.9984053,0.0005790211,0.0001993237,0.0003331364,0.0002136382,0.0002695434],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001567922,0.0002793102,0.9556297,0.0005456633,0.00006099289,0.000006829619,0.02364133,0.000002913109,0.0001484847,0.0002488717,0.00009560936,0.01918347],"study_design_scores_gemma":[0.0004287045,0.0004970715,0.9754032,0.0004790586,0.00009212596,0.000007720825,0.01334559,0.0002077923,0.004781641,0.0003628116,0.004050855,0.0003434628],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.996401,0.0003644207,0.0001770678,0.0008987437,0.0001801323,0.001799826,0.000007728671,0.0000999509,0.00007117838],"genre_scores_gemma":[0.9976102,0.00007186709,0.001105044,0.0004079016,0.00005418011,0.0001114062,0.00001891732,0.00002561253,0.0005948719],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01977343,"threshold_uncertainty_score":0.999965,"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."}}