{"id":"W2048861598","doi":"10.1145/1255175.1255233","title":"Goal-directed evaluation for the improvement of optical music recognition on early music prints","year":2007,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Leverage (statistics); Computer science; Hidden Markov model; Metric (unit); Feature extraction; Baseline (sea); Artificial intelligence; Speech recognition; Feature (linguistics); Pattern recognition (psychology); Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.001595766,0.00008403976,0.00008789889,0.00006048468,0.0001144406,0.00006108719,0.0002610298,0.00004251502,0.00008314698],"category_scores_gemma":[0.0001546795,0.00005474995,0.00004981114,0.0002372502,0.00003227032,0.0001799843,0.00005843776,0.00006580305,0.00001822939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004490713,"about_ca_system_score_gemma":0.00006292188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001740216,"about_ca_topic_score_gemma":0.00002288187,"domain_scores_codex":[0.9988892,0.00001714106,0.0002465859,0.0002479531,0.0004038742,0.0001952134],"domain_scores_gemma":[0.9989723,0.0002921673,0.0001163826,0.0002540482,0.0003263814,0.0000387141],"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":[0.000020858,0.00006568075,0.00001543394,0.00001359471,0.00001086747,2.01592e-7,0.0003246954,0.00001413716,0.01452768,0.001637583,0.000348394,0.9830209],"study_design_scores_gemma":[0.002665264,0.001126642,0.05990634,0.0001976028,0.00009882633,0.000003794168,0.0001904787,0.2778521,0.6392334,0.01734063,0.0009476842,0.0004372648],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3387716,0.00001186306,0.6543981,0.0003695151,0.000292552,0.0005621637,7.166848e-7,0.00007195467,0.00552145],"genre_scores_gemma":[0.9631826,0.000001135167,0.03562256,0.0008939859,0.0001090425,0.00004652538,0.000003159319,0.000005487323,0.0001354558],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9825836,"threshold_uncertainty_score":0.2232638,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07100568676988037,"score_gpt":0.2991381062684079,"score_spread":0.2281324194985276,"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."}}