{"id":"W4414629702","doi":"10.22541/au.175924882.28819604/v1","title":"HAND: Hierarchical Attention Network for Multi-Scale Handwritten Document Recognition and Layout Analysis","year":2025,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Field (mathematics); Convolutional neural network; Intelligent character recognition; Feature (linguistics); Document processing; Sketch recognition; Pattern recognition (psychology); Handwriting recognition; Encoder; Key (lock)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006479094,0.0001783373,0.0003142486,0.0004245809,0.0003257854,0.0004794098,0.0003089712,0.0001316677,0.00004080583],"category_scores_gemma":[0.00004090317,0.0001631068,0.000214239,0.001035164,0.00008548228,0.0004286155,0.0002082344,0.0001278942,0.00001948883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004617177,"about_ca_system_score_gemma":0.00003042831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007753675,"about_ca_topic_score_gemma":0.0003289933,"domain_scores_codex":[0.9983879,0.0001131502,0.0003863641,0.0005994824,0.0001694857,0.0003436604],"domain_scores_gemma":[0.9990927,0.0001665531,0.0000863395,0.0003432898,0.0002061503,0.0001049485],"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":[0.00006796626,0.0002744477,0.01016355,0.0001040407,0.0008308197,0.000004090896,0.0003056608,0.00002520748,0.001689619,0.009511054,0.007652304,0.9693713],"study_design_scores_gemma":[0.005148486,0.0005470287,0.0609528,0.0003266944,0.001545454,0.00001699309,0.0001318784,0.6035209,0.02334117,0.2930413,0.01007074,0.001356643],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0144056,0.0001106492,0.9821464,0.001357028,0.0001344573,0.0006085493,0.00001702942,0.0003897104,0.0008305908],"genre_scores_gemma":[0.1533431,0.00006862433,0.8418406,0.00130569,0.000082559,0.0004387402,0.0001658468,0.00001049703,0.002744337],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9680146,"threshold_uncertainty_score":0.6651301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02701011423814828,"score_gpt":0.2943456894731872,"score_spread":0.2673355752350389,"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."}}