{"id":"W4388341202","doi":"10.1007/s10489-023-04992-9","title":"Arabic text detection: a survey of recent progress challenges and opportunities","year":2023,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Arabic; Context (archaeology); Representation (politics); Natural language processing; Field (mathematics); Artificial intelligence; Semantics (computer science); Open research; Intermediate language; Data science; Linguistics; World Wide Web; Politics; Programming language; Mathematics","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":[0.0006742086,0.000102003,0.0001479387,0.0001133478,0.00005200583,0.00003349381,0.0004337782,0.00004952255,0.000009659872],"category_scores_gemma":[0.00003448825,0.00009679997,0.00001410109,0.0002929404,0.0001048078,0.0001061927,0.0002569945,0.00008614744,0.00003458589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001217286,"about_ca_system_score_gemma":0.00003847397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002435911,"about_ca_topic_score_gemma":0.00005694096,"domain_scores_codex":[0.9989862,0.0000451937,0.0002377193,0.0003317678,0.0002016654,0.0001973997],"domain_scores_gemma":[0.9991832,0.0001592269,0.0000806836,0.0004076345,0.0001083143,0.0000609301],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003908686,0.00001061535,0.00003561044,0.00002904256,0.000006518547,0.000002413597,0.0009782737,0.00005411288,0.00008530206,0.05409594,0.00000832907,0.9446899],"study_design_scores_gemma":[0.000516456,0.0007559091,0.1025258,0.0002979457,0.00003269606,0.0001052536,0.005353611,0.5135134,0.2231544,0.118572,0.03296314,0.002209405],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06343255,0.005932384,0.9200934,0.001674586,0.0005055694,0.0004856562,0.000003449619,0.000550001,0.007322471],"genre_scores_gemma":[0.9848137,0.01261282,0.002386804,0.0000406398,0.00001869577,0.00004719246,0.000001265462,0.000007037948,0.00007180391],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9424805,"threshold_uncertainty_score":0.3947388,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2370631666371304,"score_gpt":0.3112135352599225,"score_spread":0.07415036862279206,"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."}}