{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03367384,0.002747417,0.001267511,0.003891601,0.001018503,0.007212751,0.002998966,0.002787154,0.005992818],"category_scores_gemma":[0.2114028,0.000698446,0.001270374,0.001623438,0.005387035,0.008485693,0.004988975,0.002792586,0.001194298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001369681,"about_ca_system_score_gemma":0.001378444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005963393,"about_ca_topic_score_gemma":0.0006518056,"domain_scores_codex":[0.9129525,0.06643836,0.003410875,0.004380738,0.01208642,0.0007310612],"domain_scores_gemma":[0.6516389,0.294937,0.009316965,0.03039765,0.01217128,0.001538321],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003806659,0.001450913,0.005612461,0.003384262,0.0005659154,0.0002222184,0.009873869,0.02391212,0.04231667,0.07520922,0.005404279,0.8282414],"study_design_scores_gemma":[0.002168795,0.009646005,0.0132641,0.001777293,0.000688669,0.001075392,0.006521494,0.4481134,0.1435446,0.3332796,0.03873175,0.001188981],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05393114,0.0005586052,0.9314005,0.0004285804,0.0001917324,0.0009352067,0.0002414213,0.002274127,0.01003876],"genre_scores_gemma":[0.3746093,0.0002208401,0.6198373,0.0003033946,0.00009124616,0.001513222,0.0003811977,0.0007259657,0.002317453],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03367384,"threshold_uncertainty_score":0.1780864,"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."}}