{"id":"W4410491803","doi":"10.1109/jstsp.2025.3558652","title":"R-Bench: Are Your Large Multimodal Model Robust to Real-World Corruptions?","year":2025,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Signal Processing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Computer vision","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":[0.007174199,0.002039227,0.00128724,0.0009025451,0.0007116297,0.001987791,0.00197411,0.002380193,0.005143801],"category_scores_gemma":[0.03510019,0.0004074271,0.001138282,0.000656528,0.001210927,0.00320068,0.002310684,0.002736332,0.003225388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001255456,"about_ca_system_score_gemma":0.001271547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008586085,"about_ca_topic_score_gemma":0.006592916,"domain_scores_codex":[0.9969965,0.00136037,0.0001419272,0.0007814626,0.0004598867,0.0002599423],"domain_scores_gemma":[0.9940525,0.002656013,0.0004196763,0.001610174,0.0009702392,0.0002913102],"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":[0.002326674,0.0004671757,0.02066073,0.001224072,0.001134271,0.0004152421,0.0004601759,0.3278795,0.02366645,0.01050808,0.07057438,0.5406833],"study_design_scores_gemma":[0.00008500052,0.0003699444,0.004076252,0.0001492292,0.0001055088,0.0002353116,0.0002092168,0.9586479,0.01362432,0.01416981,0.00824808,0.00007939507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2401955,0.007900242,0.7018746,0.008014191,0.001566812,0.0006546977,0.006356458,0.02048413,0.01295343],"genre_scores_gemma":[0.8258098,0.001083257,0.1538036,0.002651278,0.0003864969,0.0003714699,0.009317884,0.001437794,0.005138439],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008586085,"threshold_uncertainty_score":0.03794122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04899085643834207,"score_gpt":0.3323187745233619,"score_spread":0.2833279180850199,"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."}}