{"id":"W4200356778","doi":"10.16995/dscn.8094","title":"Advances and Limitations in Open Source Arabic-Script OCR: A Case Study","year":2021,"lang":"en","type":"article","venue":"Digital Studies / Le champ numérique","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Endowment for the Humanities","keywords":"Typeface; Arabic; Open source; Humanities; Natural language processing; Artificial intelligence; Computer science; Linguistics; Art; Philosophy; Programming language; Software","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":[0.000296344,0.0002202607,0.0003823713,0.0001217419,0.0002557315,0.0008799527,0.000471314,0.00004677401,0.000001487017],"category_scores_gemma":[0.0006098588,0.0002137935,0.00004893938,0.0006247026,0.0001089805,0.002591141,0.001673628,0.0001769638,0.000009259869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006227653,"about_ca_system_score_gemma":0.0001013239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001194921,"about_ca_topic_score_gemma":0.004684949,"domain_scores_codex":[0.9983631,0.0001390549,0.0003714867,0.0006585696,0.0001743426,0.000293486],"domain_scores_gemma":[0.998669,0.0004175177,0.00009713049,0.0004112484,0.0003118722,0.00009325524],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.00001235552,0.001463432,0.01064231,0.00009850047,0.0001337609,0.00810496,0.4043387,0.0000143535,0.00004154263,0.0004675681,0.0007935429,0.573889],"study_design_scores_gemma":[0.001007981,0.0003229625,0.0004488518,0.0001080301,3.030167e-7,0.001967547,0.9513707,0.0002542039,0.0009360005,0.02412192,0.01900258,0.0004589622],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8913772,0.006221467,0.07155329,0.002600302,0.000196128,0.001346843,0.00001816081,0.0004578011,0.02622882],"genre_scores_gemma":[0.9963177,0.001118994,0.001022575,0.00027032,0.00002907012,0.0003944756,0.000005052597,0.00001694587,0.0008247938],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5734301,"threshold_uncertainty_score":0.8718245,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07025261429829413,"score_gpt":0.310846118016601,"score_spread":0.2405935037183069,"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."}}