{"id":"W4413330321","doi":"10.18280/mmep.120735","title":"Image-Based Text Translation a Fine-Tuning Using DeepSeek-Coder and Transformer Models for Multilingual Optical Character Recognition Processing","year":2025,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Transformer; Computer science; Translation (biology); Character recognition; Speech recognition; Character (mathematics); Artificial intelligence; Optical character recognition; Natural language processing; Computer vision; Image (mathematics); Engineering; Electrical engineering; Voltage; Mathematics","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":[0.0004441181,0.0002294526,0.0002838563,0.0002320579,0.000152859,0.0002948674,0.0001158922,0.0001482191,0.000001606792],"category_scores_gemma":[0.00003223888,0.0002204651,0.00006479822,0.0001865395,0.00004237995,0.0006283279,0.00001703997,0.0001948206,7.661485e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002515533,"about_ca_system_score_gemma":0.0000392747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002668313,"about_ca_topic_score_gemma":4.026066e-7,"domain_scores_codex":[0.9987068,0.00001439874,0.0004173865,0.0003986899,0.0001404376,0.0003223311],"domain_scores_gemma":[0.9993664,0.0002398394,0.0000470434,0.0001283156,0.0001282905,0.00009009041],"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":[0.00004384332,0.0002105867,0.00000214469,0.006468275,0.00005614906,0.000002980697,0.003139945,0.4146943,0.04086364,0.008343492,0.000002202511,0.5261725],"study_design_scores_gemma":[0.0005003765,0.00003421327,5.197704e-7,0.001214141,0.00004292878,0.00001100006,0.00001023307,0.9306551,0.00994955,0.05732582,0.00001376923,0.0002423179],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01965559,0.0002136927,0.9788169,0.0002207582,0.00002723408,0.0005682922,0.000005302311,0.0003790598,0.0001131225],"genre_scores_gemma":[0.355768,0.00001158279,0.644044,0.00003070472,0.00001519784,0.00009879912,0.000007172076,0.00001928138,0.000005261473],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5259302,"threshold_uncertainty_score":0.8990304,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05099759867765345,"score_gpt":0.2646587221726036,"score_spread":0.2136611234949501,"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."}}