{"id":"W2525112519","doi":"10.21700/ijcis.2016.103","title":"Word Extraction and Recognition in Arabic Handwritten Text","year":2016,"lang":"en","type":"article","venue":"International Journal of Computing and Information Sciences","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Arabic; Natural language processing; Word (group theory); Computer science; Artificial intelligence; Word recognition; Speech recognition; Linguistics; Reading (process)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001344957,0.00006848478,0.0001011043,0.0006921574,0.00007510974,0.0004005236,0.0003496928,0.00003620753,0.000008794383],"category_scores_gemma":[0.000256351,0.0000459207,0.00002548196,0.0002219523,0.0001098646,0.00730852,0.00008706135,0.00008606865,0.000008889687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003884449,"about_ca_system_score_gemma":0.00005584635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001206189,"about_ca_topic_score_gemma":0.000002321407,"domain_scores_codex":[0.9988249,0.00004985791,0.0005107269,0.00009163259,0.0004184763,0.00010443],"domain_scores_gemma":[0.9987935,0.0002453682,0.0004412309,0.00004301234,0.0004261176,0.0000507004],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000007503214,0.000010268,0.001769821,0.000002496852,0.00000473199,0.000002265557,0.00052191,0.000005048733,0.0003875471,0.001285347,0.00008338205,0.9959197],"study_design_scores_gemma":[0.01006507,0.002070644,0.5133134,0.006008603,0.00002909431,0.009294651,0.002829581,0.1204043,0.05893297,0.2415217,0.03382397,0.001706026],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4912567,0.00005260536,0.5038433,0.003338558,0.0003948764,0.00004593871,0.000001095479,0.00002960257,0.001037357],"genre_scores_gemma":[0.9731513,0.0003377729,0.02606336,0.0003671686,0.00007082659,8.206157e-7,4.452744e-7,0.000001153709,0.000007116069],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9942136,"threshold_uncertainty_score":0.5298501,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0194848364468984,"score_gpt":0.2985998062361725,"score_spread":0.2791149697892741,"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."}}