{"id":"W4393989759","doi":"10.1111/jsr.14210","title":"Evaluating the effectiveness of artificial intelligence‐based tools in detecting and understanding sleep health misinformation: Comparative analysis using Google Bard and <scp>OpenAI ChatGPT</scp>‐4","year":2024,"lang":"en","type":"article","venue":"Journal of Sleep Research","topic":"Chronic Obstructive Pulmonary Disease (COPD) Research","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Misinformation; Kurtosis; Skewness; Psychology; Artificial intelligence; Likert scale; Statistics; Mathematics; Computer 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0189888,0.0007735669,0.001096725,0.006332554,0.0005160974,0.002490175,0.000836539,0.001200664,0.0007062443],"category_scores_gemma":[0.1015902,0.0003424878,0.00143765,0.00225096,0.0009998421,0.002914774,0.001793695,0.0008983818,0.0003505942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008079177,"about_ca_system_score_gemma":0.0009093661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002250375,"about_ca_topic_score_gemma":0.003155404,"domain_scores_codex":[0.9824776,0.0105364,0.001990585,0.0008166354,0.00375358,0.0004251913],"domain_scores_gemma":[0.8128367,0.162769,0.01074075,0.002871442,0.009279743,0.001502519],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005969147,0.003997451,0.5390738,0.005512244,0.00163264,0.0007052853,0.04450009,0.002430285,0.005169836,0.000674836,0.00159451,0.3887399],"study_design_scores_gemma":[0.0004007324,0.01097788,0.9151796,0.00189107,0.001750254,0.001227161,0.02993749,0.02095013,0.009356524,0.001319869,0.00655491,0.0004544279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9943597,0.0009151523,0.00154025,0.000162638,0.00003364649,0.0003788024,0.0001450122,0.00008901564,0.002375884],"genre_scores_gemma":[0.9870494,0.001326359,0.009964885,0.0001737405,0.00004460267,0.0003194717,0.0003722629,0.00002407706,0.0007251312],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0189888,"threshold_uncertainty_score":0.1004236,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.366244225615742,"score_gpt":0.5106421402036666,"score_spread":0.1443979145879246,"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."}}