{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001781822,0.000427054,0.000533925,0.0002848094,0.0004642724,0.001520872,0.003322565,0.0001587067,0.00153108],"category_scores_gemma":[0.00007390309,0.0004035238,0.0001651971,0.0002978968,0.00006584948,0.0005920862,0.006489428,0.0008866441,0.00006570142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002184808,"about_ca_system_score_gemma":0.0004229156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001477315,"about_ca_topic_score_gemma":0.00008056678,"domain_scores_codex":[0.9959205,0.00073297,0.0004950871,0.001438611,0.0009134876,0.0004992821],"domain_scores_gemma":[0.9978101,0.0002726366,0.0002621458,0.001171269,0.000197859,0.0002860336],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002665304,0.0005771819,0.0003962429,0.0005033241,0.0002661067,0.0001104997,0.2104807,0.05919904,0.0003058221,0.4586667,0.006876956,0.2625907],"study_design_scores_gemma":[0.0009070754,0.0008170366,0.000749692,0.0006567351,0.0001542001,0.0001034697,0.06409253,0.3966115,0.004656452,0.458275,0.06734396,0.005632451],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02759815,0.00008570873,0.9440643,0.001124084,0.001549152,0.0002793111,0.0000238243,0.0003419713,0.02493346],"genre_scores_gemma":[0.101597,0.000008423596,0.8819464,0.005680393,0.0007334655,0.0001597837,0.00003525788,0.00004414256,0.009795105],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3374124,"threshold_uncertainty_score":0.9998417,"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."}}