{"id":"W2395667131","doi":"10.5072/zenodo.244224","title":"MAP Adaptation to Improve Optical Music Recognition of Early Music Documents Using Hidden Markov Models.","year":2007,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Hidden Markov model; Computer science; Adaptation (eye); Speech recognition; Maximum a posteriori estimation; Ground truth; Recall; Baseline (sea); A priori and a posteriori; Artificial intelligence; Precision and recall; Markov model; Pattern recognition (psychology); Machine learning; Markov chain; Maximum likelihood; Mathematics; Statistics","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":[0.0005179481,0.0001361547,0.0001603819,0.0001852782,0.00008936624,0.0001375146,0.0003288975,0.00007472937,0.00007809167],"category_scores_gemma":[0.00001939614,0.0001289407,0.00005298616,0.000355311,0.00002907793,0.00125105,0.0001893559,0.00008246,0.00004093985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006658697,"about_ca_system_score_gemma":0.00007780773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002072558,"about_ca_topic_score_gemma":0.00004813879,"domain_scores_codex":[0.9984865,0.00002165787,0.0003715716,0.0003987855,0.0003885432,0.0003329767],"domain_scores_gemma":[0.9992076,0.00005180311,0.0001294954,0.0002738628,0.0001953103,0.0001419876],"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":[0.00003386244,0.00006065819,0.0000266873,0.00004383937,0.00001284995,0.000008218653,0.0022924,0.000231219,0.02561208,0.002096872,0.0002813621,0.9693],"study_design_scores_gemma":[0.001461823,0.0006207627,0.001379823,0.0003485804,0.00005829043,0.00002290783,0.0006651534,0.855882,0.08548827,0.05296382,0.0001779264,0.0009306393],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3464856,0.00001216017,0.648188,0.00009851917,0.0002777048,0.0001437131,8.281137e-7,0.00005297016,0.004740551],"genre_scores_gemma":[0.6077701,3.870605e-7,0.3914764,0.0004993399,0.00007612583,0.00000274538,0.00000167871,0.000007357722,0.0001659031],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9683693,"threshold_uncertainty_score":0.525805,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05925206031133519,"score_gpt":0.2722022497220632,"score_spread":0.212950189410728,"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."}}