{"id":"W4412475991","doi":"10.3390/math13142285","title":"Toward Adaptive Unsupervised and Blind Image Forgery Localization with ViT-VAE and a Gaussian Mixture Model","year":2025,"lang":"en","type":"article","venue":"Mathematics","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"123 Certification (Canada)","funders":"","keywords":"Mixture model; Computer science; Artificial intelligence; Pattern recognition (psychology); Gaussian; Convolutional neural network; Divergence (linguistics); Autoencoder; Benchmark (surveying); Expectation–maximization algorithm; Artificial neural network; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001060759,0.0001321185,0.0001664397,0.0001198897,0.00006158798,0.0002260728,0.0001316962,0.00005904113,6.63384e-7],"category_scores_gemma":[0.00005466176,0.0001019454,0.00001684612,0.0003191448,0.00009097673,0.0004930837,0.0001248313,0.00007408569,0.000002321314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000223615,"about_ca_system_score_gemma":0.00004980098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002415987,"about_ca_topic_score_gemma":0.000008562661,"domain_scores_codex":[0.9992831,0.0000110675,0.0001580854,0.000233657,0.00016828,0.0001458372],"domain_scores_gemma":[0.9994936,0.00006672631,0.00005844347,0.0002419954,0.00007552241,0.00006370182],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002244263,0.0006594197,0.0002442976,0.002482893,0.0002906127,0.0001175109,0.04012037,0.002336211,0.001902479,0.8010132,0.002908809,0.1476998],"study_design_scores_gemma":[0.0004369859,0.00007252159,0.00002855138,0.0001656853,0.00001949597,0.00003212553,0.0002425011,0.8905278,0.001510238,0.1068071,0.0000374912,0.0001194201],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02707886,0.00005092788,0.9679547,0.0003959226,0.0000616423,0.0002381825,0.000002829516,0.0000930294,0.00412388],"genre_scores_gemma":[0.7137555,0.000009709736,0.2856885,0.0001745049,0.00001164126,0.00002036127,0.000001902255,0.00001170599,0.000326165],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8881916,"threshold_uncertainty_score":0.4157211,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01584347309708426,"score_gpt":0.2226926103081617,"score_spread":0.2068491372110775,"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."}}