{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001152265,0.0009118011,0.0003328831,0.0007944863,0.0001810013,0.001390023,0.0008355002,0.0007203528,0.002058403],"category_scores_gemma":[0.005724433,0.0002244309,0.0006952487,0.0004387188,0.0005394015,0.002278629,0.00087736,0.001277233,0.0004166033],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006536243,"about_ca_system_score_gemma":0.0004936871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004028187,"about_ca_topic_score_gemma":0.003242097,"domain_scores_codex":[0.999575,0.0001362075,0.00002110283,0.0001105297,0.0001049318,0.00005227155],"domain_scores_gemma":[0.9980929,0.001289982,0.0001700688,0.0001828334,0.0002008934,0.00006341917],"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":[0.0006075865,0.0003275958,0.008393442,0.0002902166,0.0002516193,0.0002979286,0.0004216057,0.3806147,0.05507297,0.01446106,0.001545295,0.537716],"study_design_scores_gemma":[0.0000100815,0.0001169915,0.0009953235,0.00001131032,0.00002941143,0.00005210246,0.00005197516,0.9851695,0.008214819,0.004877103,0.0004601941,0.00001107131],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1948241,0.0006293117,0.7984558,0.0006661426,0.00008003059,0.0001197614,0.0001763065,0.00181447,0.003234079],"genre_scores_gemma":[0.874967,0.0002790154,0.1229476,0.0001132502,0.00002757491,0.00004204752,0.0002504536,0.00008015368,0.001292919],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004028187,"threshold_uncertainty_score":0.008009493,"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."}}