{"id":"W2908637932","doi":"10.21083/csieci.v12i2.4227","title":"Generative Music with the Living Machine: Using Rule-Based Improvisation to Generate Narrative and Soundtrack","year":2018,"lang":"en","type":"article","venue":"Critical Studies in Improvisation / Études critiques en improvisation","topic":"Music Technology and Sound Studies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Improvisation; Performing arts; Narrative; Generative grammar; Gesture; Computer science; Generator (circuit theory); Set (abstract data type); Musical; Aesthetics; Human–computer interaction; Visual arts; Art; Artificial intelligence; Literature","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003855453,0.0005698023,0.0003861151,0.001221043,0.001527198,0.005897332,0.001971915,0.001228533,0.004277707],"category_scores_gemma":[0.01156359,0.0003204822,0.0005861229,0.0004524114,0.0100799,0.004621488,0.003683827,0.001232374,0.001016716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009402085,"about_ca_system_score_gemma":0.0009000264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008856778,"about_ca_topic_score_gemma":0.001017511,"domain_scores_codex":[0.9968623,0.001776302,0.0001387275,0.000483809,0.0006042063,0.0001348019],"domain_scores_gemma":[0.9945657,0.0037065,0.0002874107,0.0009857413,0.0002600951,0.0001945041],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002074194,0.0002178047,0.003574706,0.0006409742,0.00007832651,0.001001898,0.1163832,0.01799334,0.0313332,0.6098086,0.002428308,0.2163322],"study_design_scores_gemma":[0.0001967872,0.0005433915,0.003391287,0.0006446401,0.0001176589,0.001750105,0.03419385,0.08940212,0.04415849,0.6386603,0.1867168,0.0002245995],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1267785,0.0004692835,0.7395663,0.00140905,0.0001128242,0.000376777,0.00005382311,0.00117382,0.1300596],"genre_scores_gemma":[0.7752225,0.0002607324,0.2129977,0.0002358661,0.00003457229,0.0002513021,0.00007903645,0.0003272288,0.01059101],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005897332,"threshold_uncertainty_score":0.0203898,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0602906535225271,"score_gpt":0.3536516689663919,"score_spread":0.2933610154438648,"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."}}