{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001239782,0.0005498386,0.000691249,0.0007937869,0.003584997,0.001122023,0.000547402,0.0004006177,0.0000408431],"category_scores_gemma":[0.0001800981,0.0005277946,0.0002224154,0.001627561,0.0003385523,0.0007156828,0.00002730006,0.0009849849,0.000004025336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000161969,"about_ca_system_score_gemma":0.0002565454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000495265,"about_ca_topic_score_gemma":0.0002852676,"domain_scores_codex":[0.9968349,0.0002032897,0.0006635036,0.001112693,0.0004201882,0.0007653647],"domain_scores_gemma":[0.9978488,0.0008840291,0.0002873075,0.0005037248,0.0003625234,0.0001135906],"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":[0.0001310643,0.0003888816,0.00007337968,0.001142356,0.0003982834,0.00001740212,0.02678825,0.0008382125,0.00101764,0.0007366495,0.00008599873,0.9683819],"study_design_scores_gemma":[0.005917709,0.001210242,0.0002994341,0.002620518,0.00166396,0.00008825745,0.01749893,0.8223619,0.04106476,0.1046158,0.0004502278,0.002208304],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1234456,0.009609849,0.8637435,0.0007622606,0.0009120349,0.0006987454,0.00005275189,0.0002678647,0.000507334],"genre_scores_gemma":[0.9309446,0.0001591697,0.06531047,0.0008071895,0.00008260766,0.0001289615,0.000003163987,0.0000245137,0.00253933],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9661736,"threshold_uncertainty_score":0.9999149,"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."}}