{"id":"W2951574664","doi":"10.48550/arxiv.1807.10755","title":"A writer-independent approach for offline signature verification using deep convolutional neural networks features","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec","funders":"","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Support vector machine; Classifier (UML); Pattern recognition (psychology); Signature (topology); Machine learning; Mathematics","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"],"consensus_categories":[],"category_scores_codex":[0.0003934079,0.0004136336,0.0003790116,0.00034284,0.0003058805,0.0002350984,0.001789057,0.0007900679,0.00002006008],"category_scores_gemma":[0.00003894105,0.0004771342,0.0003253015,0.0004759363,0.000173432,0.000479931,0.001068846,0.0008425098,0.000004614192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003377047,"about_ca_system_score_gemma":0.0001506544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000488455,"about_ca_topic_score_gemma":0.00001152477,"domain_scores_codex":[0.9974771,0.0001837194,0.0002864094,0.001432683,0.0001661925,0.0004538655],"domain_scores_gemma":[0.9976231,0.0001013401,0.0004149517,0.001036107,0.0006545553,0.000169899],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003498403,0.000666964,0.001072087,0.0003975696,0.0004290991,0.0001061114,0.000336118,0.8919016,0.0005937058,0.0923849,0.003423363,0.00833861],"study_design_scores_gemma":[0.000480782,0.00007749502,0.0006029456,0.00005366454,0.00008561236,0.0000251437,0.00002205209,0.9844923,0.0003740769,0.01318602,0.00009755287,0.0005023438],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01585923,0.0001936379,0.9814946,0.00004600064,0.0005369466,0.000996549,0.00005454446,0.0005123556,0.0003061147],"genre_scores_gemma":[0.8892488,0.00003932789,0.109485,0.000167575,0.0004282701,0.00001144486,0.0003430922,0.00002968029,0.0002467404],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8733896,"threshold_uncertainty_score":0.999768,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06908249157228466,"score_gpt":0.2158572699331046,"score_spread":0.1467747783608199,"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."}}