{"id":"W4383560524","doi":"10.54254/2755-2721/4/20230490","title":"PreSoramimiset: Establishing dataset for Chinese misheard lyrics generation","year":2023,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Music and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Lyrics; Computer science; Transformer; Python (programming language); Conversation; Natural language processing; Focus (optics); Artificial intelligence; Annotation; Information retrieval; Linguistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001059188,0.001848386,0.0006774121,0.002654104,0.001344889,0.001164376,0.002115693,0.001455526,0.01123946],"category_scores_gemma":[0.003431776,0.0003293671,0.001049832,0.002077545,0.0006190092,0.001294335,0.002059964,0.001826343,0.010063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001229948,"about_ca_system_score_gemma":0.001963899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01672738,"about_ca_topic_score_gemma":0.03334082,"domain_scores_codex":[0.9985273,0.0002410264,0.000150415,0.0004393716,0.0004367687,0.0002051304],"domain_scores_gemma":[0.9984391,0.0002013001,0.00008046052,0.0004491894,0.0006078523,0.0002220252],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001135367,0.0009817113,0.01406683,0.001726272,0.0001500305,0.001100238,0.0009723555,0.005767068,0.02850012,0.003242194,0.7411655,0.2011924],"study_design_scores_gemma":[0.0007104183,0.000920519,0.1000434,0.0005458724,0.0001906419,0.001742881,0.002310152,0.06737956,0.05543943,0.002883555,0.7674026,0.0004310068],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.1395202,0.001296301,0.03838276,0.0008880037,0.001681465,0.002474082,0.7679102,0.02414127,0.02370555],"genre_scores_gemma":[0.03770621,0.0001841789,0.02192042,0.0001351903,0.00009615475,0.001155148,0.9331468,0.0003917686,0.005264112],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01672738,"threshold_uncertainty_score":0.03759974,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01823662911690549,"score_gpt":0.2383724636321235,"score_spread":0.220135834515218,"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."}}