{"id":"W2868811703","doi":"10.5958/2347-7202.2018.00002.6","title":"Multi-Character Recognition using EMNIST","year":2018,"lang":"en","type":"article","venue":"JIMS8I - International Journal of Information Communication and Computing Technology","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Innovation Cluster (Canada)","funders":"","keywords":"Character (mathematics); Character recognition; Computer science; Artificial intelligence; Natural language processing; Pattern recognition (psychology); Psychology; Mathematics; Geometry","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":[],"consensus_categories":[],"category_scores_codex":[0.0007089886,0.0001185427,0.0001686996,0.001079077,0.0002123078,0.0003210678,0.001469252,0.0001397471,0.00002114131],"category_scores_gemma":[0.0002663063,0.0001161982,0.00005864456,0.0003719683,0.0002103205,0.002215215,0.0005928487,0.0003269943,0.00004475886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009525519,"about_ca_system_score_gemma":0.00007495421,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009123532,"about_ca_topic_score_gemma":0.000002148491,"domain_scores_codex":[0.9985756,0.000084396,0.0008192654,0.00009642238,0.00029048,0.0001338073],"domain_scores_gemma":[0.9960566,0.00006337465,0.001089973,0.0003453084,0.002392077,0.00005271721],"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":[0.00002672247,0.0001039948,0.0007299329,0.000009276834,0.00009101548,0.000003210023,0.001294423,0.000006310359,0.001731923,0.01296292,0.000426375,0.9826139],"study_design_scores_gemma":[0.005265328,0.0009498612,0.00720848,0.001483945,0.00006468892,0.006123394,0.001774546,0.7822154,0.05575441,0.07087743,0.06715629,0.0011263],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07187186,0.00008186317,0.9234001,0.003356625,0.0004026845,0.00009751693,0.000003333248,0.0002181987,0.0005678395],"genre_scores_gemma":[0.5805261,0.0001097944,0.4185725,0.000708314,0.00006673066,0.0000014036,0.000008316388,0.000003691514,0.00000322531],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9814876,"threshold_uncertainty_score":0.4738425,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02912590091025083,"score_gpt":0.3092453465068082,"score_spread":0.2801194455965574,"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."}}