{"id":"W4416050620","doi":"10.61931/2224-9028.1639","title":"KADYSNET: A NOVEL APPROACH TO DYSLEXIA PREDICTION IN CHILDREN: COMBINING HANDWRITTEN TEXT RECOGNITION WITH A HYBRID CNN-BILSTM-CTC MODEL AND PERSONALIZED LEARNING STRATEGIES","year":2025,"lang":"en","type":"article","venue":"ASEAN Journal on Science and Technology for Development","topic":"Writing and Handwriting Education","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Personalization; Dyslexia; Handwriting; Sentence; Dropout (neural networks); Focus (optics); Paragraph; Key (lock)","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":[0.0003924292,0.001406576,0.0005740566,0.0009237288,0.0002052545,0.0005857819,0.001023926,0.0006917446,0.002581362],"category_scores_gemma":[0.001233644,0.0003323136,0.0005143363,0.0004919771,0.000199823,0.0008098601,0.0007906872,0.0008115411,0.001388942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007091046,"about_ca_system_score_gemma":0.001068538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01056795,"about_ca_topic_score_gemma":0.0225403,"domain_scores_codex":[0.9997165,0.0000336934,0.00001875175,0.0001334575,0.0000601874,0.0000374397],"domain_scores_gemma":[0.999693,0.00008095057,0.0000360603,0.00003558774,0.000112608,0.00004176881],"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":[0.0004281103,0.0004362136,0.02178165,0.0003460973,0.0003151787,0.0006856748,0.0001585148,0.06228476,0.04847679,0.001365676,0.02109895,0.8426223],"study_design_scores_gemma":[0.00004566868,0.0002955285,0.009455893,0.00006189424,0.0001207695,0.0003491211,0.00006152958,0.9589294,0.02271665,0.001820221,0.00610712,0.00003628445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2623167,0.003613324,0.6823239,0.0009115544,0.0006444918,0.0004409848,0.005467708,0.03292779,0.01135351],"genre_scores_gemma":[0.7764857,0.0008447682,0.2008935,0.0004939822,0.0001375592,0.0003288874,0.006444082,0.0004484162,0.01392311],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01056795,"threshold_uncertainty_score":0.02101284,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02685875003796948,"score_gpt":0.2977380783343304,"score_spread":0.270879328296361,"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."}}