{"id":"W4389510892","doi":"10.23977/jaip.2023.060802","title":"Analysis of Evaluation in Artificial Intelligence Music","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Practice","topic":"Music Technology and Sound Studies","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Music and artificial intelligence; Computer science; Rhythm; Style (visual arts); Music industry; Field (mathematics); Artificial intelligence; Musical composition; Music technology; Quality (philosophy); Popular music; Music education; Visual arts; Aesthetics; Art; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007875367,0.0001615641,0.0005309013,0.002274508,0.000131384,0.00009705501,0.000875532,0.0001471221,0.00009217148],"category_scores_gemma":[0.007462252,0.0001482672,0.0002481168,0.008271225,0.0001927597,0.001277344,0.0002247163,0.0005288631,0.00007607818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001085596,"about_ca_system_score_gemma":0.0002470004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008374712,"about_ca_topic_score_gemma":0.0004102953,"domain_scores_codex":[0.9963021,0.0004573857,0.001626021,0.0003141641,0.0009773786,0.0003228983],"domain_scores_gemma":[0.9950651,0.001912214,0.001229925,0.000474282,0.001252785,0.00006569498],"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":[0.0001581981,0.0004488258,0.0004149214,0.00001265824,0.0006648774,0.0001557586,0.01297379,0.05155139,0.00122737,0.2064333,0.0001420862,0.7258168],"study_design_scores_gemma":[0.00003039134,0.0004045447,0.002206638,0.00005891622,0.0008547864,0.00005422459,0.01366441,0.7012735,0.01265168,0.2676937,0.0008297123,0.0002775119],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2492363,0.0003452401,0.7420605,0.005921689,0.001341456,0.0002112127,0.000002241893,0.00006168194,0.0008196605],"genre_scores_gemma":[0.9904106,0.0002527458,0.009051196,0.0001567944,0.0001020882,0.000007577979,0.000001144309,0.000006144446,0.00001170344],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7411743,"threshold_uncertainty_score":0.8933552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.140090797180434,"score_gpt":0.3921649972615368,"score_spread":0.2520742000811028,"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."}}