{"id":"W4395111826","doi":"10.18280/ria.380215","title":"Decoded-ViT: A Vision Transformer Framework for Handwritten Digit String Recognition","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Numerical digit; Transformer; Digit recognition; Computer science; Speech recognition; String (physics); Pattern recognition (psychology); Artificial intelligence; Arithmetic; Engineering; Electrical engineering; Voltage; Mathematics; Artificial neural network","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005860389,0.0002709661,0.0002725745,0.0003518696,0.0002523661,0.000901461,0.0007169176,0.0002229712,0.0001962896],"category_scores_gemma":[0.0001965779,0.0002661154,0.0002931336,0.0009179929,0.00007177691,0.001219978,0.00007215433,0.0003534145,0.0009310281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009416851,"about_ca_system_score_gemma":0.00007410409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001083259,"about_ca_topic_score_gemma":0.000008954745,"domain_scores_codex":[0.9976927,0.00004895572,0.0006299,0.0008437173,0.0002518589,0.0005328597],"domain_scores_gemma":[0.9982708,0.0007436873,0.00007579662,0.0005557556,0.0001984655,0.0001555622],"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":[0.00001250518,0.00008047395,0.000003848009,0.0002030418,0.00002188956,0.0000160979,0.0009226763,0.0000699734,0.003251965,0.04759543,0.0009367423,0.9468853],"study_design_scores_gemma":[0.00003411454,0.0002664482,0.000002712579,0.001118646,0.00001954937,0.00005118858,0.0001284038,0.1638862,0.4896695,0.3207288,0.02372418,0.0003701846],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002897843,0.0006200903,0.989725,0.001875561,0.0006791578,0.0007876517,0.00003806927,0.001216768,0.002159869],"genre_scores_gemma":[0.7490318,0.0005054482,0.2482764,0.0003476965,0.0003244141,0.0004319058,0.00004661821,0.00006155963,0.0009740613],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9465152,"threshold_uncertainty_score":0.9999791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04628354131278729,"score_gpt":0.3182065916187461,"score_spread":0.2719230503059589,"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."}}