{"id":"W4414059432","doi":"10.1007/s10032-025-00555-5","title":"Optimizing identity documents classification in online systems: A comparative analysis","year":2025,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"International Medias Data Services (Canada)","funders":"","keywords":"Convolutional neural network; Context (archaeology); Identity (music); Process (computing); A priori and a posteriori; Identity management; Strengths and weaknesses","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007891015,0.0002300755,0.0005071515,0.005117055,0.0001984985,0.001902936,0.00101238,0.0001137092,0.0001085218],"category_scores_gemma":[0.00007313528,0.000200234,0.0003486486,0.003886376,0.0000696127,0.001954602,0.0002113713,0.000362847,0.00002677306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004180499,"about_ca_system_score_gemma":0.0000615162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001260417,"about_ca_topic_score_gemma":0.0002424077,"domain_scores_codex":[0.9972163,0.0002234028,0.0009704658,0.0005427836,0.0008154057,0.0002315897],"domain_scores_gemma":[0.9982194,0.0001649574,0.0006425821,0.0003311552,0.0005520002,0.00008996086],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0004786295,0.003582609,0.2421876,0.00005811837,0.05607975,0.0001959297,0.003310184,0.02718066,0.001138734,0.4208621,0.002890938,0.2420348],"study_design_scores_gemma":[0.005146771,0.0003015055,0.5337169,0.0005609625,0.005315244,0.00003257298,0.006428702,0.3551406,0.001571392,0.0813398,0.009083667,0.001361876],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3681466,0.0006720263,0.6194502,0.007474282,0.0010664,0.000314145,0.00003402764,0.0001654896,0.002676882],"genre_scores_gemma":[0.992269,0.001303655,0.005081592,0.0003818027,0.00005509639,0.00003664067,0.0001557509,0.00000354933,0.0007129302],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6241224,"threshold_uncertainty_score":0.9991332,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04133032381567437,"score_gpt":0.3529996195214886,"score_spread":0.3116692957058143,"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."}}