{"id":"W4415933829","doi":"10.1109/taslpro.2025.3629237","title":"Evaluating Sound Similarity Metrics for Differentiable, Iterative Sound-Matching","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Music Technology and Sound Studies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Metric (unit); Consistency (knowledge bases); Differentiable function; Function (biology); Similarity (geometry); Active listening; Workflow","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":[0.009139207,0.001147791,0.0008334217,0.002517395,0.0004510117,0.001885178,0.001490225,0.001513801,0.00154562],"category_scores_gemma":[0.04446955,0.000357739,0.0007741219,0.001135953,0.001244822,0.002554648,0.001802516,0.001312324,0.0005558904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009846711,"about_ca_system_score_gemma":0.000729819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001154009,"about_ca_topic_score_gemma":0.001254042,"domain_scores_codex":[0.9951692,0.001497174,0.0004881484,0.0008535042,0.001806466,0.0001855023],"domain_scores_gemma":[0.9754719,0.01769695,0.001636399,0.002528569,0.002161342,0.000504815],"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":[0.001793361,0.0007578591,0.02031336,0.0008544327,0.0003822194,0.0002033003,0.0005438654,0.3997837,0.04900793,0.01057866,0.001996194,0.5137852],"study_design_scores_gemma":[0.0001042702,0.001743153,0.007245415,0.00005215403,0.00007234533,0.0002191234,0.0001634914,0.9490048,0.03234822,0.007528057,0.001450031,0.00006890822],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3791235,0.0009602729,0.6134601,0.0001745057,0.0001049731,0.0003249213,0.0002580387,0.001622862,0.003970905],"genre_scores_gemma":[0.7256786,0.0001855686,0.2719377,0.00008677467,0.00002923456,0.0002399525,0.00053426,0.0002646047,0.001043379],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009139207,"threshold_uncertainty_score":0.04833335,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03771135256499744,"score_gpt":0.3436471715706745,"score_spread":0.305935819005677,"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."}}