{"id":"W4281671095","doi":"10.21203/rs.3.rs-1717367/v1","title":"Refocus attention span networks for handwriting line recognition","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Handwriting; Transformer; Speech recognition; Artificial intelligence; Encoder; Robustness (evolution); Lexicon; Benchmark (surveying); Natural language processing; Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":true,"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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006590079,0.0003703323,0.0004790089,0.001074546,0.001044922,0.001035867,0.001988275,0.0005127761,0.0003176374],"category_scores_gemma":[0.0008456639,0.0004095926,0.0004296949,0.001022538,0.0001138802,0.0004455744,0.004541478,0.002909056,0.00006381642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006733637,"about_ca_system_score_gemma":0.0003666661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001674414,"about_ca_topic_score_gemma":0.00004386047,"domain_scores_codex":[0.99392,0.001219941,0.0007186517,0.001510203,0.001508594,0.001122602],"domain_scores_gemma":[0.9953324,0.0008979715,0.0003048075,0.001387404,0.001822194,0.000255254],"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":[0.000073468,0.0003025203,0.0001927957,0.001230107,0.00007633332,0.00006077158,0.000214839,0.0003130751,0.0002818271,0.002005052,0.008804514,0.9864447],"study_design_scores_gemma":[0.002692815,0.003475292,0.00143858,0.006618608,0.00008343122,0.00009070577,0.0009737134,0.5652859,0.01015605,0.3497178,0.05654592,0.002921209],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003577726,0.000883474,0.9851294,0.001768858,0.0006845334,0.00365467,0.0002671605,0.00124158,0.002792563],"genre_scores_gemma":[0.7280855,0.003052824,0.236445,0.0003286714,0.003574525,0.01843012,0.00651128,0.0002833576,0.003288688],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9835235,"threshold_uncertainty_score":0.9998356,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1108915238480462,"score_gpt":0.3995111500210831,"score_spread":0.2886196261730369,"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."}}