{"id":"W2157769407","doi":"10.1145/2501115.2501123","title":"Generation of learning samples for historical handwriting recognition using image degradation","year":2013,"lang":"en","type":"preprint","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Agence Nationale de la Recherche","keywords":"Handwriting; Computer science; Artificial intelligence; Character (mathematics); Hidden Markov model; Handwriting recognition; Pattern recognition (psychology); Inkwell; Intelligent character recognition; Image (mathematics); Speech recognition; Character recognition; Computer vision; Feature extraction; 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":[0.0007100608,0.0002547818,0.000402779,0.0003766152,0.0002077944,0.0003383108,0.0004284177,0.0003256668,0.00005287757],"category_scores_gemma":[0.0004785256,0.0002717495,0.0002050729,0.0001673906,0.00003056195,0.000751135,0.0004120565,0.0003621526,0.000008932047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004963207,"about_ca_system_score_gemma":0.0001573719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006431166,"about_ca_topic_score_gemma":0.00001801235,"domain_scores_codex":[0.9978912,0.0001798573,0.0007419501,0.0006387927,0.00029943,0.0002487718],"domain_scores_gemma":[0.9976174,0.0002123281,0.0006916963,0.0003575473,0.001053723,0.00006732043],"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":[0.000007470363,0.0001291685,0.0001476306,0.0006077366,0.0000564102,0.00000116659,0.0003418853,0.0002131491,0.2241876,0.002658634,0.003061682,0.7685874],"study_design_scores_gemma":[0.0002449516,0.0001086582,0.00002824336,0.0002911799,0.0000447867,0.000009894773,0.00003565079,0.6442123,0.3320007,0.02211638,0.0004471282,0.0004600954],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0466933,0.0001047092,0.9509486,0.0001656744,0.0003796699,0.0008614184,0.00001450606,0.0004840504,0.0003480528],"genre_scores_gemma":[0.07628839,0.00006280206,0.9224544,0.00003851022,0.0003253795,0.0002644183,0.0003599512,0.00002913483,0.0001770184],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7681273,"threshold_uncertainty_score":0.9999735,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1646555369006908,"score_gpt":0.3151988945103646,"score_spread":0.1505433576096738,"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."}}