{"id":"W1501272469","doi":"","title":"Sparse descriptor for lexicon reduction in handwritten Arabic documents","year":2012,"lang":"en","type":"article","venue":"Espace ÉTS (ETS)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; École de Technologie Supérieure","funders":"","keywords":"Lexicon; Artificial intelligence; Arabic; Computer science; Histogram; Pattern recognition (psychology); Word (group theory); Natural language processing; Skeleton (computer programming); Pixel; Reduction (mathematics); Image (mathematics); Mathematics; Linguistics","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":[0.000346824,0.0004542943,0.001036648,0.002076933,0.0002815999,0.0007827672,0.0006792151,0.0003891556,0.002931075],"category_scores_gemma":[0.001623713,0.0001733189,0.0005982199,0.00191621,0.0003544364,0.0009263508,0.0007109023,0.0005059063,0.001329047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004295285,"about_ca_system_score_gemma":0.0006957922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002698585,"about_ca_topic_score_gemma":0.002801043,"domain_scores_codex":[0.99946,0.00006035817,0.00004168017,0.00007388485,0.0003104868,0.00005358291],"domain_scores_gemma":[0.9994204,0.0001739285,0.000074975,0.00008930868,0.0002077273,0.0000337064],"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":[0.0004793246,0.0001430474,0.0009894111,0.0002354716,0.00005498516,0.0001966632,0.00009161777,0.02488745,0.08088401,0.003617675,0.008322291,0.880098],"study_design_scores_gemma":[0.00008686347,0.0003869174,0.00637341,0.000041214,0.0000820058,0.0008344657,0.0002075025,0.8959195,0.07629328,0.006144895,0.01354984,0.00008007154],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1122602,0.001136975,0.8796175,0.0002236507,0.0001719685,0.0001864065,0.001063585,0.002656226,0.002683636],"genre_scores_gemma":[0.5896788,0.001425646,0.3904702,0.0002294525,0.0002823036,0.0003754517,0.006921038,0.0002843601,0.01033283],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002931075,"threshold_uncertainty_score":0.009805441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02709086643507978,"score_gpt":0.2802605596387316,"score_spread":0.2531696932036518,"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."}}