{"id":"W2896024503","doi":"10.1109/access.2018.2876035","title":"Baidu Meizu Deep Learning Competition: Arithmetic Operation Recognition Using End-to-End Learning OCR Technologies","year":2018,"lang":"en","type":"article","venue":"IEEE Access","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Connectionism; Pipeline (software); Convolutional neural network; Task (project management); Artificial intelligence; Deep learning; End-to-end principle; Recurrent neural network; Pattern recognition (psychology); Artificial neural network; Machine learning","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006642197,0.0002780383,0.0002883667,0.0006701526,0.0008278946,0.001290841,0.001232559,0.0002134229,0.0002776425],"category_scores_gemma":[0.0003278393,0.0002935941,0.00007781356,0.001179555,0.0001876886,0.002564169,0.0004826081,0.0005649602,0.0004848022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001541044,"about_ca_system_score_gemma":0.00006504554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001114037,"about_ca_topic_score_gemma":0.00007908509,"domain_scores_codex":[0.9975939,0.0002726854,0.0004475963,0.0007407874,0.0004640018,0.0004809684],"domain_scores_gemma":[0.9985027,0.0001563854,0.000225608,0.0004334058,0.0005827583,0.00009908229],"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":[0.00001447758,0.00007552616,0.0008277312,0.00003729849,0.00003024653,0.00002941014,0.0006906542,0.0006050065,0.02405677,0.0007124558,0.0001524409,0.972768],"study_design_scores_gemma":[0.0006202947,0.0007944786,0.0008955664,0.0004629883,0.00004838495,0.0002329342,0.0004389262,0.1997035,0.7753111,0.01299994,0.007377376,0.001114597],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1161791,0.00005460941,0.8771185,0.0006476566,0.0004925227,0.0003849855,0.000002491185,0.002605872,0.002514247],"genre_scores_gemma":[0.8759112,0.0000572572,0.1232449,0.0003052015,0.0002710733,0.00008811362,0.0000226781,0.0000300885,0.00006952052],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9716534,"threshold_uncertainty_score":0.9999516,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04740332064415651,"score_gpt":0.3155909041870854,"score_spread":0.2681875835429289,"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."}}