{"id":"W4319026190","doi":"10.21203/rs.3.rs-2533077/v1","title":"Signature Verification by Multi-Size Assembled-Attention with the Backbone of Swin-Transformer","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Handwriting; Artificial intelligence; Transformer; Signature (topology); Pattern recognition (psychology); Biometrics; Convolutional neural network; Feature extraction; Handwriting recognition; Block (permutation group theory); Data mining; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003569824,0.0005127637,0.0006070868,0.0003487771,0.000378225,0.000439515,0.001302824,0.000559838,0.002169901],"category_scores_gemma":[0.0007825523,0.0002505642,0.0005571874,0.0002995555,0.0004469238,0.001215736,0.0008821515,0.0006707202,0.0005898199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005684004,"about_ca_system_score_gemma":0.0006780883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006124099,"about_ca_topic_score_gemma":0.007363193,"domain_scores_codex":[0.9997742,0.00003240233,0.00001118645,0.00006641733,0.00006428676,0.00005161711],"domain_scores_gemma":[0.9996564,0.00006885971,0.00003967524,0.00008764157,0.0001052672,0.00004219579],"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":[0.0009918701,0.0003138858,0.004326544,0.0001227029,0.000144141,0.0005342892,0.0001948558,0.2026488,0.1070824,0.007686182,0.004776548,0.6711777],"study_design_scores_gemma":[0.000007705986,0.00006989163,0.000397645,0.000003209874,0.00002121874,0.00008079698,0.00001031775,0.9832512,0.01446,0.001135525,0.0005562676,0.000006243623],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2177724,0.0005666661,0.7724614,0.0003441622,0.0001318638,0.0000875537,0.00007611702,0.003132285,0.005427586],"genre_scores_gemma":[0.9456625,0.0001172017,0.04970583,0.0001550801,0.00002706824,0.00002274057,0.0001243522,0.00005674317,0.004128561],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006124099,"threshold_uncertainty_score":0.01217693,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06749547708586436,"score_gpt":0.374124492904705,"score_spread":0.3066290158188407,"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."}}