{"id":"W3038730344","doi":"10.18061/emr.v14i3-4.5576","title":"A cluster analysis of harmony in the McGill Billboard dataset","year":2020,"lang":"en","type":"article","venue":"Empirical Musicology Review","topic":"Music and Audio Processing","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Chord (peer-to-peer); Harmony (color); Active listening; Cluster analysis; Computer science; Rule-based machine translation; Cluster (spacecraft); Natural language processing; Set (abstract data type); Harmonic; Artificial intelligence; Speech recognition; Psychology; Communication; Acoustics; Art; Database; Physics; Visual arts","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.002669646,0.001262643,0.000788208,0.008386867,0.00177779,0.001826008,0.002667787,0.000924445,0.00662669],"category_scores_gemma":[0.009601451,0.0002768998,0.0009633458,0.007654765,0.0006289845,0.001084585,0.002451014,0.0008665564,0.003582108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002798515,"about_ca_system_score_gemma":0.001984249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1339751,"about_ca_topic_score_gemma":0.3272957,"domain_scores_codex":[0.9975863,0.0006106557,0.0001509595,0.0006138022,0.0007643931,0.000273922],"domain_scores_gemma":[0.9964888,0.001003041,0.0002622287,0.0006357842,0.001318402,0.0002917836],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.001070543,0.0003004822,0.0525456,0.002336488,0.0004928664,0.0005342155,0.003140831,0.00384314,0.009470294,0.00514931,0.6273052,0.293811],"study_design_scores_gemma":[0.0002948933,0.0002781055,0.4536898,0.000757206,0.0003297427,0.0005308674,0.007402104,0.02292892,0.005769269,0.005877567,0.5018125,0.0003290629],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.3329747,0.0115533,0.03142981,0.003443238,0.0009266851,0.001669676,0.581048,0.005793978,0.03116073],"genre_scores_gemma":[0.2175245,0.001466712,0.07510206,0.0006052576,0.0002702209,0.001855849,0.6925487,0.0007325787,0.009894077],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1339751,"threshold_uncertainty_score":0.2663906,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1498637346831151,"score_gpt":0.3684217534184395,"score_spread":0.2185580187353244,"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."}}