{"id":"W4409364374","doi":"10.1609/aaai.v39i16.33918","title":"Enhance Vision-Language Alignment with Noise","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Noise (video); Computer vision; Artificial intelligence; Image (mathematics)","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":[0.0003350328,0.000201632,0.0002050689,0.0001358557,0.0002275576,0.0002286792,0.002249014,0.00005892643,0.00003800604],"category_scores_gemma":[0.0002008787,0.0001375988,0.00006766708,0.0009588222,0.0002228664,0.0002462368,0.0004382392,0.0002984,0.00009327448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005499429,"about_ca_system_score_gemma":0.0001104029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001637786,"about_ca_topic_score_gemma":0.00001294856,"domain_scores_codex":[0.9983495,0.00001708199,0.0003823031,0.0005475313,0.0004268632,0.0002766849],"domain_scores_gemma":[0.9986463,0.0001111934,0.000272436,0.0005132727,0.0003922405,0.00006460001],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003386652,0.0001543991,0.0003447671,0.00002847185,0.00001350656,2.608549e-7,0.0009821545,0.0001646404,0.06874523,0.8393064,0.0001154063,0.09011097],"study_design_scores_gemma":[0.00003899115,0.0001974507,0.002219888,0.0004414306,0.00001532016,0.000002154418,0.0004204123,0.1106907,0.8237264,0.06176519,0.0002397384,0.0002424113],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4758892,0.00005662848,0.4197095,0.0291684,0.0003626524,0.001202618,0.000005291884,0.0003397915,0.07326597],"genre_scores_gemma":[0.9868169,0.000009590896,0.01194103,0.0004173401,0.00002159472,0.0000784682,3.177282e-7,0.00000827113,0.0007064997],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7775412,"threshold_uncertainty_score":0.5611116,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01975103152251084,"score_gpt":0.3212355657977287,"score_spread":0.3014845342752179,"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."}}