{"id":"W2144026429","doi":"10.1109/icdar.2001.953836","title":"Character recognition experiments using Unipen data","year":2002,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Backpropagation; Computer science; Pattern recognition (psychology); Handwriting; Artificial intelligence; Cursive; Classifier (UML); Character recognition; Handwriting recognition; Artificial neural network; Speech recognition; Training set; Representation (politics); Optical character recognition; Feature extraction","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001816362,0.0001069597,0.0001021478,0.0001132696,0.00008669122,0.0002014494,0.001148818,0.00005544879,0.001776372],"category_scores_gemma":[0.00002431886,0.0001007495,0.00002338671,0.0002269958,0.00002107683,0.00209413,0.0006001047,0.0000820294,0.001019647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003054104,"about_ca_system_score_gemma":0.000008518902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003037678,"about_ca_topic_score_gemma":0.000001565055,"domain_scores_codex":[0.9989276,0.00005584665,0.0001925125,0.0004241506,0.0001969282,0.0002029578],"domain_scores_gemma":[0.9987648,0.00002548384,0.00006434267,0.001003649,0.00006839119,0.00007332786],"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":[0.000001681349,0.0002267887,0.0001123798,0.000008309244,0.00002252412,0.00002483032,0.0004290935,8.464124e-8,0.02269167,0.0006140826,0.01528976,0.9605788],"study_design_scores_gemma":[0.0008293614,0.0001275842,0.0002754614,0.0001313384,0.00002018614,0.0001994101,0.00007848832,0.4580191,0.4955002,0.006206308,0.03760484,0.001007682],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02448933,0.00006994176,0.9413934,0.0005161237,0.0002637467,0.0002898715,0.00001842836,0.001027491,0.03193168],"genre_scores_gemma":[0.3411302,0.00007972884,0.654891,0.002197728,0.0001664778,0.00002387712,0.00009766724,0.00002151631,0.001391746],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9595711,"threshold_uncertainty_score":0.9997582,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2512199841090454,"score_gpt":0.332919803090206,"score_spread":0.08169981898116058,"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."}}