{"id":"W3086773305","doi":"10.1007/978-3-030-66823-5_16","title":"L2-Constrained RemNet for Camera Model Identification and Image Manipulation Detection","year":2020,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Preprocessor; Block (permutation group theory); Artificial intelligence; Convolutional neural network; Identification (biology); Categorical variable; Image (mathematics); Pattern recognition (psychology); Standard test image; Computer vision; Image processing; Machine learning; 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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007560835,0.0003374014,0.0003243867,0.0005226368,0.0002010267,0.001467892,0.001215914,0.0002235508,3.431071e-7],"category_scores_gemma":[0.0005165928,0.0003545,0.00008497849,0.000972292,0.0003953044,0.001298626,0.001218095,0.0004805034,0.000004120284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002579227,"about_ca_system_score_gemma":0.0003182504,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004262835,"about_ca_topic_score_gemma":0.00008833857,"domain_scores_codex":[0.996801,0.00004619694,0.000517016,0.001648944,0.0005675853,0.0004192835],"domain_scores_gemma":[0.9982399,0.0002236392,0.0002539056,0.0008276325,0.0003017277,0.0001531716],"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":[0.000011582,0.0000191985,0.00002467937,0.0001026941,0.000005442783,0.000003576813,0.0007752458,0.1811952,0.02814416,0.0004408478,0.000004017274,0.7892734],"study_design_scores_gemma":[0.0001916591,0.0000753857,0.0006532094,0.00006360584,0.000006905238,0.00002173826,6.240076e-7,0.800893,0.04922463,0.148587,0.000003580158,0.0002785999],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02792282,0.000036484,0.9666825,0.001537561,0.002544409,0.0009730152,0.00001089255,0.0002787421,0.00001356435],"genre_scores_gemma":[0.621085,0.000003939547,0.3784507,0.0002124978,0.0001657757,0.00005895919,0.00001041406,0.0000121325,5.572413e-7],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7889947,"threshold_uncertainty_score":0.9998907,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02430020699921155,"score_gpt":0.2625143461586354,"score_spread":0.2382141391594239,"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."}}