{"id":"W4407697469","doi":"10.1016/j.inffus.2025.104092","title":"VLDBench Evaluating multimodal disinformation with regulatory alignment","year":2025,"lang":"en","type":"preprint","venue":"Information Fusion","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University; Toronto Zoo; Vector Institute","funders":"","keywords":"Disinformation; Benchmark (surveying); Computer science; Artificial intelligence; Natural language processing; Geography; World Wide Web; Cartography; Social media","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002139804,0.0003123615,0.0002927333,0.0005481589,0.0009880695,0.0006963717,0.0004359234,0.0004772941,0.0006595164],"category_scores_gemma":[0.0004985253,0.0002742036,0.0001105874,0.0003982384,0.000130745,0.003865926,0.0003685961,0.0004669624,0.000273053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007316179,"about_ca_system_score_gemma":0.001641423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009100563,"about_ca_topic_score_gemma":0.000149655,"domain_scores_codex":[0.9962775,0.0001743274,0.001037371,0.0001652014,0.001920404,0.0004252171],"domain_scores_gemma":[0.9974075,0.00009606216,0.00102618,0.0005105002,0.0007413654,0.0002183717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002241243,0.00007246488,0.0002774493,0.0008171698,0.00008136994,5.48485e-7,0.3985899,0.044032,0.00001562022,0.02862724,0.02345963,0.5038025],"study_design_scores_gemma":[0.005524495,0.0004409212,0.02555905,0.004563391,0.0002848067,0.000007342208,0.1279137,0.2609318,0.0009063525,0.003455612,0.5676041,0.002808477],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2880589,0.00005035261,0.02152174,0.002347667,0.002122696,0.003144821,0.0001837111,0.0006755091,0.6818946],"genre_scores_gemma":[0.9835813,0.0002718766,0.007402936,0.0023847,0.000306092,0.00007535578,0.001934008,0.00001365773,0.004030042],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6955224,"threshold_uncertainty_score":0.999971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02982611508341688,"score_gpt":0.3501096435763882,"score_spread":0.3202835284929713,"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."}}