{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003072644,0.0002890503,0.000352094,0.00036931,0.0002736419,0.0003705141,0.002075785,0.0004851947,0.00004564222],"category_scores_gemma":[0.0002548505,0.0001996159,0.0001815253,0.001292482,0.0001917646,0.0003282273,0.0005719183,0.002081185,0.0001286144],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001628376,"about_ca_system_score_gemma":0.0003746721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000252666,"about_ca_topic_score_gemma":0.00009570707,"domain_scores_codex":[0.9954641,0.0007732047,0.0004161556,0.0008980171,0.001871584,0.0005769194],"domain_scores_gemma":[0.9957845,0.0007666264,0.0002221861,0.001493881,0.001606008,0.000126784],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002664725,0.001829012,0.001915434,0.006292905,0.0006982782,0.00008727111,0.004778889,0.0001583035,0.6474748,0.007064758,0.1889597,0.1404742],"study_design_scores_gemma":[0.003790668,0.002442711,0.09592707,0.009302272,0.0001477476,0.00003680503,0.002716624,0.03388479,0.8081192,0.02055657,0.0202193,0.002856252],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02335514,0.0007769048,0.958978,0.01082871,0.0002130645,0.003774385,0.0002012105,0.0009345606,0.0009380116],"genre_scores_gemma":[0.9720024,0.0008877859,0.02290823,0.00005649368,0.00009002529,0.001112736,0.0002287915,0.00007423375,0.002639273],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9486473,"threshold_uncertainty_score":0.9041829,"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."}}