{"id":"W3213260946","doi":"10.1093/llc/fqaa058","title":"Lessons learned in a large-scale project to digitize and computationally analyze musical scores","year":2020,"lang":"en","type":"article","venue":"Digital Scholarship in the Humanities","topic":"Music and Audio Processing","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Marianopolis College","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Multidisciplinary approach; Computer science; Data science; Scale (ratio); Big data; Musical; Software; Data mining; Sociology; Social science; Visual arts","routes":{"ca_aff":true,"ca_fund":true,"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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003805287,0.0001445934,0.000181405,0.0001413532,0.0001871889,0.003348699,0.0007207564,0.00003777947,0.000004206386],"category_scores_gemma":[0.0002590207,0.0001141594,0.00003840564,0.0005553772,0.000102639,0.001806981,0.0003549708,0.0003061689,0.00002195053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002499257,"about_ca_system_score_gemma":0.00009990124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001353716,"about_ca_topic_score_gemma":0.0001767488,"domain_scores_codex":[0.9986535,0.00009094318,0.0002344492,0.0003804688,0.000341298,0.0002993585],"domain_scores_gemma":[0.999482,0.0002098524,0.00005012168,0.0001613184,0.00004440468,0.00005233664],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0001562702,0.0007165241,0.07467856,0.0003607722,0.00004772979,0.0004422439,0.3994271,0.0009304718,0.0001869908,0.2621055,0.001607484,0.2593404],"study_design_scores_gemma":[0.003847946,0.0008565111,0.6410084,0.001065293,0.0000229478,0.0001061782,0.02025573,0.03520447,0.0002326376,0.2425724,0.05257577,0.002251692],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9721537,0.0001270786,0.01000601,0.01037857,0.00003628059,0.0002702968,0.00002732736,0.0000977893,0.0069029],"genre_scores_gemma":[0.9893873,0.000002554706,0.001295877,0.009137681,0.00007001668,0.00002270825,0.00001081171,0.00000885197,0.000064163],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5663298,"threshold_uncertainty_score":0.9976859,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1168915003145781,"score_gpt":0.3200639208922122,"score_spread":0.2031724205776341,"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."}}