{"id":"W4404720546","doi":"10.3390/info15120751","title":"Exploring the Impact of Image-Based Audio Representations in Classification Tasks Using Vision Transformers and Explainable AI Techniques","year":2024,"lang":"en","type":"article","venue":"Information","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Transformer; Computer science; Artificial intelligence; Computer vision; Audio visual; Speech recognition; Multimedia; Engineering; Electrical engineering","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":[0.0006462006,0.00009295696,0.00008926898,0.0004514006,0.0001278225,0.0003904542,0.0002052636,0.00003427138,0.000004261763],"category_scores_gemma":[0.00006430411,0.00007013737,0.00005490139,0.000936288,0.00006481686,0.01053652,0.00003290769,0.0001327162,0.000008929727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001856483,"about_ca_system_score_gemma":0.0001429395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00111054,"about_ca_topic_score_gemma":0.00002078507,"domain_scores_codex":[0.9990433,0.00005335563,0.000412393,0.0001270021,0.0001957612,0.0001681272],"domain_scores_gemma":[0.9994026,0.0001226515,0.00008245283,0.0002336094,0.0001284423,0.00003019421],"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":[0.00005141573,0.00007120459,0.0007854484,0.0003263267,0.00002674732,0.000006357402,0.03266713,0.03491288,0.1029787,0.03952735,0.0004058873,0.7882405],"study_design_scores_gemma":[0.00004456161,0.00007088943,0.003477834,0.0001196924,0.000003659583,0.000005116779,0.001203275,0.8965932,0.09650873,0.001682397,0.000207134,0.0000835567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2215216,0.00002666974,0.7763247,0.0007547074,0.0000702072,0.0003282693,0.000003037964,0.000110041,0.0008608537],"genre_scores_gemma":[0.9904631,0.00004309096,0.009355333,0.00003748768,0.00001211983,0.000072507,0.000008605193,0.000004623192,0.00000312086],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8616803,"threshold_uncertainty_score":0.7638721,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08433699312779384,"score_gpt":0.3697730099991448,"score_spread":0.285436016871351,"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."}}