{"id":"W3095237147","doi":"10.1016/j.eswa.2020.114196","title":"A comprehensive comparison of end-to-end approaches for handwritten digit string recognition","year":2020,"lang":"en","type":"preprint","venue":"Expert Systems with Applications","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"Fundação Araucária; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fondo Nacional de Desarrollo Científico y Tecnológico; Nvidia","keywords":"Segmentation; Computer science; Heuristics; String (physics); End-to-end principle; Artificial intelligence; Pipeline (software); Sequence (biology); NIST; Pattern recognition (psychology); Benchmark (surveying); Representation (politics); Machine learning; Speech recognition; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001744449,0.0004895596,0.001033988,0.0003620739,0.0002240421,0.000408074,0.001457128,0.0003114216,0.000005439048],"category_scores_gemma":[0.00003267341,0.0004681282,0.0002025663,0.0005882873,0.0001040593,0.000240221,0.0007379713,0.0004127158,0.00004311916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001457787,"about_ca_system_score_gemma":0.0002367598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002028515,"about_ca_topic_score_gemma":0.00001351697,"domain_scores_codex":[0.996626,0.0001182759,0.001033375,0.001297435,0.0005420758,0.0003828196],"domain_scores_gemma":[0.9964671,0.0003625405,0.0008230472,0.00129838,0.0007575739,0.0002913573],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002254653,0.001580729,0.0003524596,0.006286875,0.0012017,0.000006156372,0.01807158,0.002058014,0.009275895,0.04072837,0.0214431,0.8987697],"study_design_scores_gemma":[0.004032854,0.002412316,0.000466462,0.007337304,0.0004143394,0.0001402577,0.009490154,0.2080252,0.2958485,0.03246095,0.4332605,0.006111236],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007074093,0.000860943,0.9871323,0.001102029,0.0001458379,0.007845426,0.0004967821,0.0008142514,0.0008950887],"genre_scores_gemma":[0.6917082,0.00003274479,0.277005,0.0001534175,0.0003523644,0.02988261,0.0007527592,0.00006629454,0.00004664122],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8926584,"threshold_uncertainty_score":0.999777,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1278187303993129,"score_gpt":0.3236232059702125,"score_spread":0.1958044755708996,"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."}}