{"id":"W2995555793","doi":"10.1016/j.aci.2019.12.001","title":"Inpainting forgery detection using hybrid generative/discriminative approach based on bounded generalized Gaussian mixture model","year":2019,"lang":"en","type":"article","venue":"Applied Computing and Informatics","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Inpainting; Discriminative model; Computer science; Artificial intelligence; Generative grammar; Generative model; Probabilistic logic; Pattern recognition (psychology); Mixture model; Bounded function; Support vector machine; Gaussian; Image (mathematics); Statistical model; Machine learning; Computer vision; 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"],"consensus_categories":[],"category_scores_codex":[0.0004729682,0.0002921062,0.0003137142,0.0002678011,0.0003159615,0.0005047462,0.0002864397,0.00009425751,5.204315e-7],"category_scores_gemma":[0.00004842562,0.0002653006,0.00006937092,0.0003454433,0.00006328485,0.0006315085,0.0002065446,0.000297888,0.000009783109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001195455,"about_ca_system_score_gemma":0.00008306093,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005304791,"about_ca_topic_score_gemma":3.65231e-7,"domain_scores_codex":[0.9983222,0.00003494752,0.0005267999,0.0003059365,0.0004049946,0.000405079],"domain_scores_gemma":[0.9988938,0.0001047176,0.0003617351,0.0004145098,0.000113621,0.0001116125],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004553815,0.00009604435,0.00002348074,0.0002776335,0.00004661992,0.000001309021,0.004922194,0.6782817,0.003264647,0.04203046,0.0001156706,0.2708947],"study_design_scores_gemma":[0.0006824851,0.0001016986,0.00001569209,0.00004972852,0.00001049916,0.00001636903,0.0003367387,0.9831682,0.01240095,0.002831149,0.00006705531,0.0003194174],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3512679,0.000002939594,0.6385355,0.00002378809,0.0002371164,0.0002929556,0.00000157846,0.0001644151,0.009473798],"genre_scores_gemma":[0.6989818,5.366647e-7,0.3001312,0.0007867406,0.0000525472,0.000006688195,0.00001151903,0.00001450712,0.00001453879],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3477138,"threshold_uncertainty_score":0.9999799,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01396364807436192,"score_gpt":0.2202785375486626,"score_spread":0.2063148894743007,"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."}}