{"id":"W2228104382","doi":"10.5539/mas.v9n13p148","title":"A Bilingual Numeral OCR System for Creating Uni-Lingual Digitized Numeral Document","year":2015,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Numeral system; Computer science; Tamil; Optical character recognition; Natural language processing; Artificial intelligence; Document processing; Arabic numerals; Speech recognition; Linguistics; Image (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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002410478,0.0003140161,0.0003799784,0.0003222513,0.0006561307,0.001173142,0.002135489,0.00009470426,0.000005086972],"category_scores_gemma":[0.000267847,0.0002884661,0.000101229,0.0009572072,0.000351035,0.001017915,0.0006210132,0.0001947866,0.000053253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004996501,"about_ca_system_score_gemma":0.001463127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005697047,"about_ca_topic_score_gemma":0.000006585051,"domain_scores_codex":[0.996163,0.00004652573,0.0005543762,0.001146398,0.001175085,0.0009146115],"domain_scores_gemma":[0.9976639,0.0001482585,0.0002386197,0.0008129087,0.0005292418,0.0006070422],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001986236,0.0002306017,0.0001691225,0.0001944243,0.00004667265,0.00004966594,0.02043576,0.0006027464,0.2309356,0.3827994,0.0007038099,0.3636335],"study_design_scores_gemma":[0.00233122,0.0002759045,0.00001845936,0.0001227106,0.00001810326,0.00009665534,0.0009079427,0.517702,0.3847519,0.09184488,0.00103091,0.0008992944],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07142491,0.00003098442,0.9131479,0.0001472834,0.000360442,0.0009756879,0.000009564152,0.001561016,0.01234223],"genre_scores_gemma":[0.8258879,7.779057e-7,0.1732153,0.0002472656,0.0001412804,0.0002516081,0.000004904356,0.00002129553,0.0002296052],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.754463,"threshold_uncertainty_score":0.9999567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02906896390302306,"score_gpt":0.2884901105079798,"score_spread":0.2594211466049567,"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."}}