{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005442224,0.00137213,0.002035066,0.00954142,0.001031626,0.005042571,0.002170765,0.001321859,0.004817014],"category_scores_gemma":[0.01169772,0.0006318198,0.0008673994,0.006631591,0.001138718,0.007585037,0.001656858,0.001576241,0.003986047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009882485,"about_ca_system_score_gemma":0.001986741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003145903,"about_ca_topic_score_gemma":0.002870853,"domain_scores_codex":[0.9970504,0.000650479,0.0003124877,0.0007421608,0.001086961,0.0001574509],"domain_scores_gemma":[0.986858,0.007128385,0.0006532309,0.0005911062,0.004301443,0.0004676824],"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":[0.00010007,0.000104112,0.003322822,0.002669928,0.00005350918,0.00005737304,0.0003283262,0.0008050529,0.003096599,0.003549997,0.02594624,0.9599659],"study_design_scores_gemma":[0.00006070005,0.0005632964,0.01530829,0.003259423,0.0005838267,0.002375811,0.004651608,0.08186313,0.02681851,0.03077578,0.8333972,0.000342562],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.02114983,0.7956457,0.1371316,0.01684459,0.003000527,0.0003104932,0.001688252,0.004328481,0.01990042],"genre_scores_gemma":[0.1761553,0.6090459,0.1744196,0.00511433,0.009993691,0.0003478935,0.006706683,0.0007636411,0.01745309],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.00954142,"threshold_uncertainty_score":0.02878153,"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."}}