{"id":"W2128273046","doi":"10.1109/ccece.1999.808042","title":"A new comprehensive database of handwritten Arabic words, numbers, and signatures used for OCR testing","year":2003,"lang":"en","type":"article","venue":"","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Arabic; Natural language processing; Artificial intelligence; Optical character recognition; Character recognition; Speech recognition; Image (mathematics); Linguistics","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":[],"consensus_categories":[],"category_scores_codex":[0.0001296228,0.00009759791,0.000146097,0.00005807256,0.00006652743,0.00006730827,0.0002467037,0.00004226483,0.0000107062],"category_scores_gemma":[0.0001892399,0.0000798119,0.000031289,0.0003166135,0.00004022928,0.000278155,0.00006125176,0.00006636918,0.000001424503],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008396009,"about_ca_system_score_gemma":0.0000839711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006642136,"about_ca_topic_score_gemma":0.000005039715,"domain_scores_codex":[0.999254,0.00003366364,0.0001767348,0.0002557228,0.000131709,0.0001481448],"domain_scores_gemma":[0.9990128,0.0003594935,0.00008992643,0.0002920117,0.0001703233,0.00007544096],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000250789,0.0001267234,0.00180732,0.00023967,0.00004875528,0.000006225423,0.0006588193,0.000002856504,0.4907019,0.3904331,0.01912874,0.09682082],"study_design_scores_gemma":[0.001300432,0.0002586472,0.001642989,0.0001415469,0.0000239753,0.00002984581,0.000202357,0.01069674,0.9401273,0.02218117,0.02295038,0.0004446753],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00166502,0.0004799454,0.9958862,0.0002681617,0.00004174596,0.000279651,0.000005409323,0.0001506476,0.001223184],"genre_scores_gemma":[0.2198296,0.0000192247,0.7789636,0.0002401029,0.00001729129,0.00001137156,0.000004089345,0.000006706691,0.0009080688],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4494254,"threshold_uncertainty_score":0.3254635,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03966937779737517,"score_gpt":0.2832628990313947,"score_spread":0.2435935212340196,"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."}}