{"id":"W2099926249","doi":"10.1016/s0031-3203(00)00098-4","title":"A lexicon-driven approach for optimal segment combination in off-line recognition of unconstrained handwritten Korean words","year":2001,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Korea Science and Engineering Foundation","keywords":"Computer science; Lexicon; Artificial intelligence; Segmentation; Pattern recognition (psychology); Word (group theory); Classifier (UML); Intelligent word recognition; Handwriting recognition; Line (geometry); Speech recognition; Text segmentation; Image (mathematics); Character recognition; Feature extraction; Intelligent character recognition; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008548358,0.0003161349,0.0004475367,0.0006927165,0.00009519018,0.0001167384,0.0004401971,0.0002248888,0.00008442828],"category_scores_gemma":[0.0001073923,0.0003444451,0.0001870754,0.0006757123,0.00009551246,0.0008711502,0.0001085644,0.0002368574,0.00003236134],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001612842,"about_ca_system_score_gemma":0.00008791335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008130213,"about_ca_topic_score_gemma":0.00006707302,"domain_scores_codex":[0.9973646,0.0002115242,0.000868008,0.0006971693,0.0003968345,0.0004618213],"domain_scores_gemma":[0.9984083,0.0001943724,0.0004279919,0.0003551572,0.0004966337,0.0001175556],"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":[0.00007999955,0.0008236963,0.001465276,0.0001270069,0.00003450828,0.000009666905,0.0005316151,0.0000302473,0.002195347,0.00004733819,0.0001020644,0.9945532],"study_design_scores_gemma":[0.01594309,0.003543085,0.004734938,0.001762653,0.0001746154,0.0003681061,0.001136266,0.6593489,0.2582903,0.05220034,0.0002160148,0.002281673],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.215266,0.00003256955,0.7812663,0.000351874,0.0001207151,0.001334786,0.0001577516,0.000258406,0.00121158],"genre_scores_gemma":[0.8324044,0.0001276001,0.1645615,0.0002617679,0.0001020331,0.0007794012,0.001694637,0.00003325807,0.00003533867],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9922715,"threshold_uncertainty_score":0.9999008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04208097509528119,"score_gpt":0.2732928643360469,"score_spread":0.2312118892407657,"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."}}