{"id":"W2057330140","doi":"10.1145/1753326.1753328","title":"Estimating residual error rate in recognized handwritten documents using artificial error injection","year":2010,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Residual; Handwriting; Word error rate; Handwriting recognition; Set (abstract data type); Speech recognition; Measure (data warehouse); Artificial intelligence; Pattern recognition (psychology); Data mining; Feature extraction; Algorithm","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":[0.002483559,0.0007014895,0.0006863183,0.001834104,0.0001972482,0.000833975,0.0008828982,0.001085206,0.0005598891],"category_scores_gemma":[0.02664617,0.0003311672,0.0004207609,0.001257984,0.000541513,0.0009952901,0.0005708261,0.0006651753,0.0004073498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003943226,"about_ca_system_score_gemma":0.0003204345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007766134,"about_ca_topic_score_gemma":0.0006617807,"domain_scores_codex":[0.9957997,0.001001305,0.0005661255,0.0007159876,0.001712428,0.0002045086],"domain_scores_gemma":[0.9527327,0.02764142,0.008463772,0.005334787,0.005315535,0.0005116824],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003578894,0.001248323,0.1227277,0.0006279673,0.0003983087,0.0009972356,0.001384828,0.1325451,0.375867,0.0011587,0.0009737224,0.3584924],"study_design_scores_gemma":[0.00004000192,0.001731345,0.05347339,0.00004007997,0.0001248115,0.001521694,0.0001345259,0.5909433,0.350754,0.0004510606,0.000658796,0.0001269458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7686983,0.0003030791,0.2269758,0.00004396524,0.00004965881,0.0001663807,0.0001916512,0.002751978,0.0008191131],"genre_scores_gemma":[0.9090478,0.00009688535,0.0897209,0.00003015366,0.00001238389,0.00006888997,0.0002421731,0.0001445096,0.0006361937],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.002483559,"threshold_uncertainty_score":0.01313448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03983830630952655,"score_gpt":0.3224563889916165,"score_spread":0.28261808268209,"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."}}