{"id":"W4306679606","doi":"10.1609/aiide.v18i1.21960","title":"Controlling Perceived Emotion in Symbolic Music Generation with Monte Carlo Tree Search","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Music and Audio Processing","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Discriminator; Monte Carlo method; Beam search; Decoding methods; Monte Carlo tree search; Classifier (UML); Artificial intelligence; Language model; Search algorithm; Machine learning; Algorithm; Statistics; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002397463,0.0001915575,0.0002291285,0.0001738047,0.0002580659,0.0005140899,0.0005886986,0.00002574241,0.00003003332],"category_scores_gemma":[0.0000472094,0.0001410778,0.00006407151,0.0003323034,0.0001123957,0.001064186,0.0003770789,0.0003155263,0.000003416312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001619322,"about_ca_system_score_gemma":0.00006133023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000567646,"about_ca_topic_score_gemma":0.00001521708,"domain_scores_codex":[0.9983813,0.00002636994,0.0003757565,0.0004646856,0.0004851935,0.0002667001],"domain_scores_gemma":[0.9993193,0.00004674863,0.000221987,0.0001309444,0.0002236791,0.00005734518],"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":[0.001000048,0.001334478,0.003908342,0.00009220365,0.0001129821,0.00001090553,0.05853657,0.007074066,0.1377575,0.11692,0.00009130094,0.6731616],"study_design_scores_gemma":[0.0003406445,0.001606147,0.002357369,0.0004998746,0.00001771559,0.00004158443,0.02279737,0.8508716,0.1153802,0.005515814,0.00008805335,0.0004835554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9852169,0.00001573896,0.008842252,0.001564729,0.0001394459,0.0003986978,0.000005994332,0.00002180875,0.003794429],"genre_scores_gemma":[0.9992775,0.00001085297,0.000128002,0.0003180985,0.00003688389,0.00006537302,0.000001463591,0.000009385505,0.0001524734],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8437976,"threshold_uncertainty_score":0.5752985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05871401786779438,"score_gpt":0.2650276179272189,"score_spread":0.2063136000594245,"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."}}