{"id":"W4313201936","doi":"10.1007/s10032-022-00422-7","title":"Refocus attention span networks for handwriting line recognition","year":2022,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Computer science; Handwriting; Transformer; Artificial intelligence; Speech recognition; Encoder; Robustness (evolution); Lexicon; Natural language processing; Benchmark (surveying); Pattern recognition (psychology)","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":[0.001833745,0.0002592695,0.00035864,0.001536889,0.0008534792,0.001083818,0.0006719006,0.00008689681,0.0008414431],"category_scores_gemma":[0.0001072649,0.000251176,0.0005616695,0.0008110849,0.00004020517,0.0009257261,0.000277807,0.0005413669,0.0000243553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003277574,"about_ca_system_score_gemma":0.00004665384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000283425,"about_ca_topic_score_gemma":0.00001683154,"domain_scores_codex":[0.9968929,0.0003136936,0.0008747788,0.0005798468,0.0009969366,0.0003418206],"domain_scores_gemma":[0.9977266,0.0002351917,0.0007449065,0.0002070187,0.0008975998,0.0001887188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001857981,0.0002962142,0.0005634888,0.000006945524,0.001459404,0.0000593203,0.0001088567,0.0005269838,0.0002927803,0.0006192375,0.001123653,0.9947573],"study_design_scores_gemma":[0.01767744,0.007615735,0.008345911,0.001030432,0.004769905,0.00330249,0.00174973,0.4185463,0.02255429,0.443772,0.06582633,0.004809438],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06501989,0.0001703719,0.9285123,0.003739685,0.001219438,0.0003911724,0.0001124684,0.0001909554,0.0006436731],"genre_scores_gemma":[0.970692,0.0009932509,0.02349178,0.001838942,0.001016866,0.0003113369,0.00102238,0.00002976958,0.0006037148],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9899479,"threshold_uncertainty_score":0.999994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02054236969264456,"score_gpt":0.2856094053117104,"score_spread":0.2650670356190658,"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."}}