{"id":"W2800600340","doi":"10.3390/app8050654","title":"Deep Neural Networks for Document Processing of Music Score Images","year":2018,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Music and Audio Processing","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Social Sciences and Humanities Research Council of Canada; Universidad de Alicante","keywords":"Computer science; Digitization; Convolutional neural network; Artificial intelligence; Artificial neural network; Field (mathematics); Deep learning; Process (computing); Classifier (UML); Machine learning; Pattern recognition (psychology); Speech recognition; Computer vision","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":[],"consensus_categories":[],"category_scores_codex":[0.0005804208,0.0001202016,0.0001576942,0.00008030704,0.0005925688,0.0003211491,0.001053288,0.00003459489,0.00001287165],"category_scores_gemma":[0.00001600904,0.00009149338,0.0000379929,0.0007273523,0.0007582786,0.0005622557,0.0002013735,0.00005384109,0.000002808645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001059865,"about_ca_system_score_gemma":0.00007687011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004458979,"about_ca_topic_score_gemma":0.000006098462,"domain_scores_codex":[0.998624,0.00001050096,0.000229516,0.0004535468,0.0003052254,0.0003771927],"domain_scores_gemma":[0.999368,0.0000680002,0.0001993206,0.0001998693,0.00010548,0.00005930767],"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":[0.000009967432,0.00003287584,0.0002582056,0.00007071201,0.000005031269,7.023148e-7,0.001802145,0.002746424,0.00559717,0.03432972,0.0009812376,0.9541658],"study_design_scores_gemma":[0.0003300907,0.0002091324,0.0006354543,0.00005169644,0.000009698866,0.000006277852,0.0002503697,0.9495483,0.02640216,0.0217665,0.0005012389,0.0002890602],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02452474,0.000273868,0.9685153,0.0004216516,0.0002727407,0.0002098575,2.137678e-7,0.00007370649,0.005707865],"genre_scores_gemma":[0.9098446,0.000001400886,0.08903268,0.0008248245,0.000237959,0.00002814277,3.689838e-7,0.00000438945,0.0000256281],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9538767,"threshold_uncertainty_score":0.455762,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02942553726443466,"score_gpt":0.2716329150582529,"score_spread":0.2422073777938182,"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."}}