{"id":"W2958816042","doi":"10.48550/arxiv.1907.04352","title":"Exploring Conditioning for Generative Music Systems with Human-Interpretable Controls","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Music Technology and Sound Studies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"MIDI; Piano; Recurrent neural network; Computer science; Polyphony; Set (abstract data type); Generator (circuit theory); Representation (politics); Speech recognition; Process (computing); Generative grammar; Artificial intelligence; Artificial neural network; Machine learning; Psychology; Programming language; Power (physics)","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":[0.0009366598,0.0005452036,0.0003976606,0.0003043509,0.0004413789,0.001768898,0.000724341,0.000718387,0.01406897],"category_scores_gemma":[0.005083479,0.0002904858,0.0008110815,0.0002499088,0.00283871,0.002259841,0.001663991,0.001358213,0.0004778735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008838018,"about_ca_system_score_gemma":0.0003874002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001382381,"about_ca_topic_score_gemma":0.001127853,"domain_scores_codex":[0.9992842,0.0002326265,0.00002279084,0.000193822,0.0001718586,0.00009467385],"domain_scores_gemma":[0.9979552,0.001466411,0.0001255642,0.0002469531,0.0001102825,0.00009558492],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000581771,0.0001079848,0.001811282,0.0003438661,0.0001161605,0.000394279,0.001272673,0.1422785,0.04991665,0.7534642,0.001847464,0.04786517],"study_design_scores_gemma":[0.00008962151,0.0001884649,0.002077767,0.000054023,0.00004101544,0.0001745557,0.0002394191,0.3796783,0.01347723,0.5956705,0.008242847,0.00006630028],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1544008,0.0008468176,0.8101429,0.001214604,0.0001588421,0.00006827371,0.0002386791,0.0007232639,0.03220588],"genre_scores_gemma":[0.960974,0.0002154891,0.03474937,0.000114892,0.00005642484,0.00003682783,0.0001109034,0.0001466028,0.00359549],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01406897,"threshold_uncertainty_score":0.04706538,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1819201349985089,"score_gpt":0.2033207651194343,"score_spread":0.02140063012092536,"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."}}