{"id":"W4416154085","doi":"10.1016/j.patcog.2026.114258","title":"ProtoSig: Enhancing training data for offline handwritten signature verification using prototypical signatures","year":2025,"lang":"en","type":"article","venue":"Pattern Recognition","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":"Training (meteorology); Signature (topology); Training set; Pattern recognition (psychology); Feature (linguistics); Identification (biology)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009349115,0.0002758767,0.0003137031,0.0003608743,0.0002990069,0.000331959,0.001165756,0.0003052824,0.00003128866],"category_scores_gemma":[0.000387469,0.0002795226,0.00009679935,0.0005216106,0.00005067296,0.00114536,0.000301885,0.0003881946,0.00001666861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009018241,"about_ca_system_score_gemma":0.0001967827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001964234,"about_ca_topic_score_gemma":0.00002393353,"domain_scores_codex":[0.9975798,0.0001699933,0.0005623072,0.0009812736,0.0002844517,0.0004221436],"domain_scores_gemma":[0.9980875,0.0002558786,0.0002320489,0.0009330533,0.0004096733,0.00008179323],"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":[0.00004323108,0.0001166919,0.00005127086,0.0002609778,0.00004520221,0.00000315243,0.00023239,0.000003035992,0.07672452,0.0001379856,0.0007888288,0.9215927],"study_design_scores_gemma":[0.002167066,0.0003218534,0.0006016603,0.002207248,0.000149914,0.00003126413,0.0001959043,0.3548542,0.5946151,0.03605257,0.007748186,0.001055059],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007547858,0.0001217614,0.9856996,0.0007923817,0.0003095757,0.004439773,0.0001989732,0.0006198976,0.0002702048],"genre_scores_gemma":[0.684875,0.00001946764,0.3090911,0.001514437,0.0003555265,0.002531658,0.001519178,0.00003951901,0.00005407789],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9205377,"threshold_uncertainty_score":0.9999657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08839965685597474,"score_gpt":0.3367099570313951,"score_spread":0.2483103001754203,"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."}}