{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001024762,0.0009113181,0.001637404,0.00462281,0.0008589022,0.001393187,0.001379659,0.0008936002,0.01211221],"category_scores_gemma":[0.00260514,0.0004127531,0.0005556748,0.002505535,0.0003010182,0.00256003,0.001140604,0.0007490937,0.009164399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004545007,"about_ca_system_score_gemma":0.001601064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002083599,"about_ca_topic_score_gemma":0.00399448,"domain_scores_codex":[0.9985966,0.0000980346,0.0001923428,0.0003001198,0.00073901,0.00007388906],"domain_scores_gemma":[0.9960808,0.0002765754,0.0002319573,0.0009411542,0.002127108,0.00034247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001012389,0.000908387,0.005734911,0.0007413639,0.0001071715,0.0005783339,0.0001545166,0.003016977,0.1514617,0.001877128,0.06586245,0.7685447],"study_design_scores_gemma":[0.0004080815,0.002199764,0.09688731,0.000440124,0.0005625008,0.008645011,0.000505603,0.05012553,0.2789876,0.003245828,0.5575351,0.0004576203],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.2829866,0.007548849,0.4702729,0.0007886942,0.001788151,0.004366323,0.1498844,0.02815371,0.05421031],"genre_scores_gemma":[0.2087552,0.003110032,0.4233647,0.0006866796,0.0004254864,0.002500055,0.3146779,0.001204553,0.04527546],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.01211221,"threshold_uncertainty_score":0.04051936,"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."}}