{"id":"W4387543532","doi":"10.1145/3616195.3616201","title":"A Free Verbalization Method of Evaluating Sound Design: The Effectiveness of Artificially Intelligent Natural Language Processing Methods and Tools","year":2023,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science; Variety (cybernetics); Natural (archaeology); Sound (geography); Connotation; Process (computing); Human–computer interaction; Sound design; Natural language; Artificial intelligence; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.008807178,0.00009563761,0.0001972318,0.00008648891,0.0001230643,0.0001709845,0.0004273497,0.00003597987,0.000003375101],"category_scores_gemma":[0.00147413,0.00006200317,0.00003627946,0.0008126251,0.00006213271,0.0004175921,0.0002894978,0.00007880767,5.030757e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001508154,"about_ca_system_score_gemma":0.0001071425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002092354,"about_ca_topic_score_gemma":0.000002894173,"domain_scores_codex":[0.9977624,0.001309089,0.0002759746,0.0002399757,0.0002667842,0.0001457849],"domain_scores_gemma":[0.9967319,0.002609714,0.0001887851,0.0002741327,0.0001748798,0.00002054064],"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":[0.00001958721,0.000009514783,0.00003487914,0.000285069,0.0000137257,7.276151e-7,0.00404948,0.002363872,0.1669684,0.004423615,0.000007534849,0.8218236],"study_design_scores_gemma":[0.0001017342,0.0000396889,0.0007882594,0.0001330377,0.00001435541,0.000003922671,0.0004837645,0.6088619,0.3729925,0.01651117,0.000002442161,0.00006722253],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02340246,0.0006999472,0.9751625,0.00008071992,0.0001046745,0.0002488604,5.867917e-7,0.00007132844,0.0002288943],"genre_scores_gemma":[0.4927465,0.000002281203,0.5071603,0.00004079653,0.00001337617,0.000009763015,8.336212e-7,0.000004907417,0.00002121414],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8217564,"threshold_uncertainty_score":0.3052409,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1057284000693283,"score_gpt":0.4368069633195104,"score_spread":0.331078563250182,"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."}}