{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006949612,0.0001774999,0.0003296201,0.0003369912,0.001212128,0.001195578,0.002213061,0.00007541128,0.0001600805],"category_scores_gemma":[0.0004447074,0.0001898311,0.0000818516,0.0008618647,0.0001078197,0.0003391269,0.004628298,0.0003202917,0.00005755686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008246555,"about_ca_system_score_gemma":0.00001655155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002711043,"about_ca_topic_score_gemma":0.000001818199,"domain_scores_codex":[0.9978694,0.0002955477,0.0004238374,0.0009427465,0.0002469339,0.000221532],"domain_scores_gemma":[0.9974514,0.0001176546,0.0004260903,0.00128712,0.0005754466,0.0001422557],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001590105,0.0006200096,0.00008331115,0.001414822,0.002032421,0.000004820532,0.01502666,0.002035324,0.006751342,0.1099978,0.2373954,0.6244792],"study_design_scores_gemma":[0.00155793,0.0007146611,0.01916258,0.0004594867,0.0007130368,0.00003408264,0.0009393892,0.1262721,0.001272565,0.01482857,0.8327474,0.001298145],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002304269,0.0000746535,0.9788787,0.01142197,0.0001102279,0.0005885706,0.003375531,0.0004051384,0.002840882],"genre_scores_gemma":[0.9778578,0.00006703712,0.01397274,0.0008389235,0.0001238314,5.242437e-7,0.00663454,0.0003703036,0.0001343296],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9755535,"threshold_uncertainty_score":0.9998413,"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."}}