{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01927972,0.0001702793,0.0007113874,0.00190851,0.0003759806,0.0002892874,0.0001822334,0.00008023207,0.0000264645],"category_scores_gemma":[0.001796219,0.0001233554,0.0001697137,0.003111077,0.0004968493,0.0005337032,0.0001601693,0.001230826,0.000001619076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001685088,"about_ca_system_score_gemma":0.00102275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001775842,"about_ca_topic_score_gemma":0.00006076752,"domain_scores_codex":[0.994594,0.001978017,0.0009311685,0.0002863535,0.001681262,0.0005292281],"domain_scores_gemma":[0.9908265,0.007711274,0.0002719029,0.0002148715,0.0007038081,0.0002716272],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.009789511,0.001226389,0.08320322,0.02573322,0.008411454,0.001090763,0.0563646,0.2326256,0.07337324,0.0126782,0.00004315504,0.4954606],"study_design_scores_gemma":[0.0007328718,0.001128516,0.05653182,0.002179271,0.0002850627,0.0001365914,0.0356939,0.8947029,0.004831233,0.00369488,0.000008418106,0.00007456392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9703332,0.005334768,0.02270371,0.000395318,0.00007343225,0.0008983435,0.00001228226,0.000007053283,0.0002418541],"genre_scores_gemma":[0.9985871,0.0001011232,0.001145717,0.00001316219,0.0001190881,0.000009756825,0.000004639312,0.00001520164,0.000004204293],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6620772,"threshold_uncertainty_score":0.6682006,"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."}}