{"id":"W1971709796","doi":"10.1007/s100320100056","title":"A generic method of cleaning and enhancing handwritten data from business forms","year":2001,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal; École de Technologie Supérieure; Concordia University","funders":"","keywords":"Computer science; Handwriting; Thresholding; Artificial intelligence; Task (project management); Workload; Automation; Natural language processing; Image (mathematics)","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":[0.001059701,0.001447844,0.001669361,0.002796126,0.0007874239,0.00209958,0.002068343,0.001801603,0.004600287],"category_scores_gemma":[0.002464355,0.0007193431,0.001960428,0.00256967,0.0008135472,0.001683894,0.001920315,0.001368487,0.007726496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000389578,"about_ca_system_score_gemma":0.00112799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001540271,"about_ca_topic_score_gemma":0.003171623,"domain_scores_codex":[0.9983947,0.0001043052,0.0001428538,0.0004237147,0.000793062,0.0001414793],"domain_scores_gemma":[0.9976816,0.0002733844,0.000200571,0.0009447979,0.0008158614,0.00008377949],"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":[0.000149103,0.0001241985,0.000881871,0.0004880048,0.000117373,0.0002001038,0.0001392765,0.002460549,0.1911059,0.001706126,0.006816606,0.7958109],"study_design_scores_gemma":[0.0000709722,0.0003651554,0.009925902,0.00009872553,0.0003177634,0.003600226,0.0002235107,0.1672934,0.7279857,0.004355877,0.08557419,0.0001886082],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004131644,0.0002667759,0.9871333,0.00005399179,0.000116268,0.0001364739,0.0003200383,0.007196259,0.0006452146],"genre_scores_gemma":[0.01917891,0.0003285806,0.9725609,0.00008562836,0.000067435,0.0001205869,0.0011665,0.0006739909,0.005817578],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004600287,"threshold_uncertainty_score":0.0153895,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03368209746036197,"score_gpt":0.3181661943383481,"score_spread":0.2844840968779861,"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."}}