{"id":"W4390421642","doi":"10.2139/ssrn.4676554","title":"Evaluating the Effectiveness of AI-based Tools in Detecting and Understanding Sleep Health Misinformation: Comparative Analysis Using Google Bard and OpenAI ChatGPT","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Misinformation; Data science; Computer science; Computer security","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":[0.005832408,0.0007740676,0.0007108594,0.007803471,0.0006206125,0.002390354,0.001030057,0.001307359,0.001200955],"category_scores_gemma":[0.05481929,0.000252123,0.0007773257,0.003381407,0.0005493453,0.003999114,0.001567919,0.0007539256,0.0005320264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007513067,"about_ca_system_score_gemma":0.00113842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01372315,"about_ca_topic_score_gemma":0.01210251,"domain_scores_codex":[0.9959586,0.002139094,0.0004342491,0.0002948418,0.001001386,0.0001717724],"domain_scores_gemma":[0.8746421,0.1145659,0.00404891,0.00147753,0.004160706,0.001104841],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.008674091,0.004594258,0.4806069,0.005456761,0.001601765,0.0007764105,0.01730664,0.005191132,0.003550927,0.001613501,0.005565288,0.4650624],"study_design_scores_gemma":[0.0007671555,0.009013218,0.8391151,0.001546781,0.002936269,0.001610717,0.03191473,0.08434837,0.008350521,0.004362053,0.015411,0.0006240017],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9876131,0.001288955,0.002208358,0.0003756875,0.00004725324,0.0002863317,0.0009275313,0.0005013102,0.006751527],"genre_scores_gemma":[0.9879126,0.001143396,0.008372647,0.0001629724,0.00004200634,0.0001350625,0.001252568,0.00003700201,0.0009416901],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01372315,"threshold_uncertainty_score":0.03084505,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3747503432029693,"score_gpt":0.5193200534269402,"score_spread":0.1445697102239709,"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."}}