{"id":"W4406070280","doi":"10.1007/s10115-024-02321-1","title":"Fake news detection: comparative evaluation of BERT-like models and large language models with generative AI-annotated data","year":2025,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":43,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University; Vector Institute","funders":"","keywords":"Computer science; Generative grammar; Language model; Fake news; Artificial intelligence; Natural language processing; Generative model; Information retrieval","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":[0.001564973,0.0001186443,0.000230736,0.0002291479,0.0003844259,0.000235608,0.0001335461,0.00009229562,0.00001342326],"category_scores_gemma":[0.00006084869,0.00009491987,0.00001373393,0.0004591992,0.00009327559,0.00764628,0.00006590888,0.00008607855,0.00001022797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007114086,"about_ca_system_score_gemma":0.0003629762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006241133,"about_ca_topic_score_gemma":0.002479651,"domain_scores_codex":[0.9985892,0.0002679859,0.000457043,0.0001150184,0.0004094291,0.0001613891],"domain_scores_gemma":[0.9984338,0.00005632556,0.0002415698,0.0002314806,0.0009519738,0.0000848679],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001018245,0.00006054897,0.00008707841,0.0003083211,0.0001598504,1.043115e-7,0.8193449,0.008169045,0.00002971821,0.122927,0.01010598,0.0387056],"study_design_scores_gemma":[0.001151203,0.00003690513,0.0001333035,0.00011439,0.00005034362,0.000001558639,0.1116527,0.8543628,0.0000923136,0.0001899843,0.03209783,0.0001166195],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1731239,0.003618072,0.2474,0.0003202005,0.0006045795,0.002519645,0.000306707,0.0001258876,0.571981],"genre_scores_gemma":[0.9988016,0.00013548,0.00007013625,0.0001786714,0.0000378712,0.0000179741,0.0001871253,0.000002574368,0.000568554],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8461938,"threshold_uncertainty_score":0.5543369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1036317786528191,"score_gpt":0.3879677179702772,"score_spread":0.2843359393174581,"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."}}