{"id":"W4412711493","doi":"10.2196/72524","title":"Performance of Large Language Models in the Cognitive Analysis of Misinformation: Evaluation Study","year":2025,"lang":"en","type":"article","venue":"JMIR Infodemiology","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Misinformation; Cognition; Psychology; Computer science; Computer security; World Wide Web","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":[],"consensus_categories":[],"category_scores_codex":[0.004818038,0.00005444503,0.0002276663,0.0004306789,0.00008539842,0.000007897213,0.0001947498,0.00007676602,0.0001086379],"category_scores_gemma":[0.0006513585,0.00003998448,0.00005550515,0.001434453,0.00009500955,0.0003715068,0.00003032191,0.00009105219,0.000002533131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003983855,"about_ca_system_score_gemma":0.0001846625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003770519,"about_ca_topic_score_gemma":0.001147405,"domain_scores_codex":[0.9984792,0.0005304977,0.0004930867,0.00006008616,0.0002933498,0.0001437482],"domain_scores_gemma":[0.9989463,0.0003833774,0.0002528819,0.0001428471,0.0002586689,0.00001593672],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.00007293483,0.0001930737,0.1861776,0.00002445494,0.000150408,9.603258e-8,0.7787464,0.01221755,0.00000391074,0.01608197,0.0001814006,0.006150231],"study_design_scores_gemma":[0.0005426535,0.00005963126,0.5923221,0.00001521431,0.000146667,4.478691e-8,0.2205426,0.1861124,0.000008856342,0.0001798948,0.00003284589,0.0000371163],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9223361,0.00002825405,0.0002551567,0.0001798058,0.00003263209,0.0006654413,0.00001027379,0.00000733694,0.07648499],"genre_scores_gemma":[0.9993463,0.00001848415,0.00001615172,0.0005146385,0.000006022626,0.00002595428,0.00002494805,7.621168e-7,0.00004673425],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5582038,"threshold_uncertainty_score":0.1669845,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05879326106579951,"score_gpt":0.4525299982837979,"score_spread":0.3937367372179984,"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."}}