{"id":"W4392354806","doi":"10.18280/ria.380101","title":"Data Augmentation for Offline Arabic Handwritten Text Recognition Using Moving Least Squares","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Handwriting; Artificial intelligence; Convolutional neural network; Task (project management); Deep learning; Handwriting recognition; Arabic; Generative grammar; Natural language processing; Artificial neural network; Speech recognition; Pattern recognition (psychology); Feature extraction; Linguistics","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":[0.0009725904,0.0002311541,0.0002288725,0.0003562326,0.0002742744,0.0006954953,0.001099831,0.0001138699,0.0001511979],"category_scores_gemma":[0.000236981,0.0002385077,0.0001159464,0.0007955873,0.00007422363,0.00137041,0.000344532,0.0002032047,0.0004337641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001122516,"about_ca_system_score_gemma":0.0001092164,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004844359,"about_ca_topic_score_gemma":0.00002656064,"domain_scores_codex":[0.9976779,0.00008108677,0.0006358535,0.0009644854,0.0002384463,0.0004022942],"domain_scores_gemma":[0.998172,0.0003861601,0.0001254183,0.0009741662,0.0002409245,0.0001013192],"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":[0.00001412793,0.00009629159,0.00001164556,0.0003074726,0.00003199192,0.00001779479,0.0006504497,0.00130758,0.02049959,0.002366761,0.001894024,0.9728023],"study_design_scores_gemma":[0.00004098684,0.0001016397,0.000003939711,0.0005743853,0.00003103198,0.00006740992,0.0002748937,0.8839585,0.09511258,0.01410009,0.005445258,0.000289269],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007167723,0.0008262543,0.9883242,0.0009399703,0.0006291625,0.0006928911,0.0001769483,0.0007493969,0.0004934652],"genre_scores_gemma":[0.6880793,0.0001961208,0.3094412,0.0002977221,0.0005372179,0.0001679,0.0005095734,0.00006321055,0.0007076872],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.972513,"threshold_uncertainty_score":0.9726062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.137066026589948,"score_gpt":0.347834769432749,"score_spread":0.210768742842801,"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."}}