{"id":"W4220991114","doi":"10.31234/osf.io/t3pf9","title":"Best-worst scaling, an alternative method to assess perceptual sound qualities","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Alberta","keywords":"Perception; Sound (geography); Active listening; Psychology; Scaling; Psychoacoustics; Duration (music); Rating scale; Computer science; Cognitive psychology; Mathematics; Acoustics; Communication; Developmental psychology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01053576,0.001587261,0.000913969,0.002221517,0.0005786989,0.001471625,0.0007608965,0.0009178314,0.009892158],"category_scores_gemma":[0.04382828,0.0003150916,0.0007054167,0.001602296,0.0008995141,0.002795892,0.001227105,0.0008170857,0.002272171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002111915,"about_ca_system_score_gemma":0.0002303665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003385999,"about_ca_topic_score_gemma":0.0006438933,"domain_scores_codex":[0.990521,0.004488158,0.0009901534,0.001319086,0.002508191,0.0001734907],"domain_scores_gemma":[0.9656786,0.02055748,0.003422532,0.004204079,0.005502617,0.0006345398],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.007084351,0.0009746019,0.03446359,0.003382909,0.0007431179,0.0002832061,0.005314554,0.00369443,0.2637283,0.01047865,0.00777872,0.6620737],"study_design_scores_gemma":[0.001597417,0.03420082,0.4482956,0.001483927,0.001389452,0.003842269,0.01065871,0.113843,0.22123,0.07773551,0.08383474,0.001888582],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.266658,0.002144271,0.6930912,0.0002735147,0.000944493,0.001589334,0.001326215,0.001753974,0.03221898],"genre_scores_gemma":[0.6907705,0.0006760707,0.3004507,0.0002928592,0.0003130313,0.002089661,0.0007490476,0.0006026517,0.004055466],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01053576,"threshold_uncertainty_score":0.05571908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2155297321381529,"score_gpt":0.4340840135015102,"score_spread":0.2185542813633572,"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."}}