{"id":"W2051284700","doi":"10.1016/j.patcog.2014.04.025","title":"Arabic word descriptor for handwritten word indexing and lexicon reduction","year":2014,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Lexicon; Computer science; Word (group theory); Natural language processing; Artificial intelligence; Search engine indexing; Speech recognition; Context (archaeology); Reduction (mathematics); Word recognition; Arabic; Pattern recognition (psychology); Mathematics; Linguistics; Reading (process)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006746784,0.0002320968,0.0002450842,0.0002877841,0.0002389571,0.0003612021,0.0002796736,0.0001604127,0.00003428333],"category_scores_gemma":[0.0001305425,0.0002426869,0.00009023956,0.0002299412,0.00006295481,0.001015732,0.0001007296,0.0001900681,0.00007567386],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006088497,"about_ca_system_score_gemma":0.00002513048,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003769821,"about_ca_topic_score_gemma":0.00001973551,"domain_scores_codex":[0.9982663,0.0001443805,0.0003693649,0.0006330127,0.0002135656,0.0003733848],"domain_scores_gemma":[0.9989834,0.0001411978,0.0001919254,0.000313308,0.0002358238,0.0001342934],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001308819,0.00003951958,0.0002951688,0.00005987851,0.0000127325,7.316002e-7,0.0002300197,1.851767e-7,0.00484918,0.0000993092,0.000532794,0.9938674],"study_design_scores_gemma":[0.006160794,0.001642957,0.01643974,0.002019884,0.0001961068,0.0006167151,0.0004055902,0.05470283,0.5308254,0.3621693,0.02164117,0.003179563],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1558948,0.00004949567,0.8412848,0.0008198896,0.0004584293,0.000555402,0.00001287975,0.0005464377,0.0003779822],"genre_scores_gemma":[0.9302967,0.00006123285,0.06779619,0.0006661285,0.0004614023,0.000445827,0.00009041716,0.0000345269,0.0001476337],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9906878,"threshold_uncertainty_score":0.9896485,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0314805224316948,"score_gpt":0.2533956168225437,"score_spread":0.2219150943908489,"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."}}