{"id":"W3086036193","doi":"10.5281/zenodo.4245459","title":"Data quality matters: Iterative corrections on a corpus of Mendelssohn string quartets and implications for MIR analysis","year":2020,"lang":"en","type":"preprint","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; String (physics); License; Chord (peer-to-peer); Workflow; Information retrieval; Key (lock); Quality (philosophy); Music information retrieval; Natural language processing; Database; Musical; Mathematics; Physics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.039147,0.001543584,0.001544473,0.007463285,0.004111758,0.006283042,0.003136411,0.001786372,0.005738095],"category_scores_gemma":[0.2429297,0.001006874,0.00132461,0.007610038,0.003119673,0.005027753,0.007552976,0.003071088,0.005611305],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002056554,"about_ca_system_score_gemma":0.00380557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00496938,"about_ca_topic_score_gemma":0.009049477,"domain_scores_codex":[0.9590817,0.01547982,0.004045103,0.008397442,0.01195491,0.001040993],"domain_scores_gemma":[0.7645671,0.1355752,0.01026357,0.04326773,0.04441274,0.001913617],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002121016,0.0004026222,0.04599165,0.004574414,0.000582291,0.002622077,0.03366061,0.008522208,0.09422736,0.01100175,0.0664157,0.7298784],"study_design_scores_gemma":[0.0003610824,0.0007359804,0.1246145,0.002381277,0.0007801088,0.003992923,0.02424113,0.08054912,0.196919,0.0468695,0.5176653,0.0008901861],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4074208,0.00566975,0.4993825,0.007921228,0.003000522,0.00151064,0.01783088,0.0393766,0.01788712],"genre_scores_gemma":[0.3321546,0.0008817592,0.6095487,0.001458444,0.0004748385,0.001046252,0.02981063,0.0156544,0.00897033],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.039147,"threshold_uncertainty_score":0.2070316,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1806515882362803,"score_gpt":0.3505100913547485,"score_spread":0.1698585031184681,"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."}}