{"id":"W2129766592","doi":"10.1016/j.patcog.2011.10.011","title":"Dynamic selection of generative–discriminative ensembles for off-line signature verification","year":2011,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Discriminative model; Computer science; Pattern recognition (psychology); Signature (topology); Classifier (UML); Artificial intelligence; Hidden Markov model; Feature selection; Generative model; Subspace topology; Machine learning; Selection (genetic algorithm); Codebook; Generative grammar; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002862131,0.000171949,0.0001933169,0.000246999,0.00009807727,0.00003444899,0.0002634992,0.0001418879,0.0001067202],"category_scores_gemma":[0.00006616836,0.0001722781,0.0001012159,0.000271815,0.00004272137,0.0005882208,0.00003941077,0.0001273103,0.00002871632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005971225,"about_ca_system_score_gemma":0.00003639778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002787391,"about_ca_topic_score_gemma":0.00005557576,"domain_scores_codex":[0.9987472,0.0001229274,0.0003530464,0.0004074002,0.0001743642,0.0001950452],"domain_scores_gemma":[0.9986956,0.00008400356,0.0003058319,0.0002012085,0.0006651686,0.00004816237],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002541511,0.0001691141,0.0000763139,0.00006599418,0.00002692169,7.421353e-7,0.0009649087,5.980323e-7,0.05392648,0.0001716451,0.0001973255,0.9443746],"study_design_scores_gemma":[0.0004410927,0.0007083928,0.002583775,0.0001104849,0.00003724735,0.00001333701,0.00008716823,0.03732976,0.9366,0.02172983,0.00008650011,0.0002724206],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06058731,0.00006635343,0.9375572,0.0001050483,0.00015772,0.0006353591,0.00008355814,0.0002444515,0.0005630087],"genre_scores_gemma":[0.8173258,0.00009376353,0.1818087,0.0001275059,0.00003847295,0.0003019077,0.000239092,0.00001786411,0.00004679362],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9441021,"threshold_uncertainty_score":0.7025298,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05284061859672254,"score_gpt":0.2807842239529998,"score_spread":0.2279436053562773,"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."}}