{"id":"W4296700181","doi":"10.1016/j.scijus.2022.09.003","title":"An efficient method to detect series of fraudulent identity documents based on digitised forensic data","year":2022,"lang":"en","type":"article","venue":"Science & Justice","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"Internal Security Fund - Police; Israel Science Foundation; Université de Lausanne; European Commission","keywords":"Computer science; False positive paradox; Profiling (computer programming); Forensic science; Information retrieval; Crime scene; Series (stratigraphy); Data mining; Identity (music); Computer security; Artificial intelligence; Criminology; Psychology","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":[0.003121339,0.000181873,0.0002115752,0.0005248224,0.0006164453,0.000538778,0.004997359,0.00002116715,0.00002426036],"category_scores_gemma":[0.0008946934,0.0001813282,0.00004381349,0.003398549,0.00030299,0.003500218,0.002353933,0.0001755217,0.00003020718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002673332,"about_ca_system_score_gemma":0.0004351909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009279133,"about_ca_topic_score_gemma":0.00003367887,"domain_scores_codex":[0.9953471,0.0001742811,0.0003464538,0.001146613,0.002451549,0.0005340098],"domain_scores_gemma":[0.996641,0.0001954784,0.0001873283,0.002438761,0.0002134696,0.0003239648],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001951254,0.0005580582,0.0001010898,0.00009773835,0.00001053847,0.00006472792,0.001505796,0.4164976,0.02062364,0.0266171,0.0006664959,0.5330622],"study_design_scores_gemma":[0.0005293512,0.002364176,0.00307819,0.00004695314,0.0000519834,0.0000380668,0.0006177201,0.9260166,0.0612888,0.003576449,0.001951104,0.000440632],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1035365,0.000007951541,0.8909098,0.00027588,0.002975162,0.0004528151,0.00008537308,0.0001645244,0.001592],"genre_scores_gemma":[0.8167212,3.186363e-7,0.1826064,0.0005514275,0.00003549349,0.00003673814,0.00000809888,0.000009679582,0.00003065291],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7131847,"threshold_uncertainty_score":0.9286419,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02542539394928056,"score_gpt":0.3260618365553703,"score_spread":0.3006364426060897,"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."}}