{"id":"W4396611084","doi":"10.21203/rs.3.rs-4320842/v1","title":"Enhancing Practicality and Efficiency of Deepfake Detection.","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Key (lock); Inference; Convolutional neural network; Artificial intelligence; Enhanced Data Rates for GSM Evolution; Image (mathematics); Machine learning; Core (optical fiber); Computer security","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003542458,0.001784128,0.001094596,0.002396637,0.001324568,0.002841072,0.002223562,0.002668214,0.01206427],"category_scores_gemma":[0.03094468,0.0007258478,0.0005953126,0.00120535,0.001578943,0.005721712,0.005453588,0.002151988,0.004775129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007210078,"about_ca_system_score_gemma":0.001984175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001134717,"about_ca_topic_score_gemma":0.002234283,"domain_scores_codex":[0.9952187,0.001541589,0.0002110294,0.0006512775,0.00184661,0.0005307816],"domain_scores_gemma":[0.9820973,0.009782371,0.0006896529,0.004231253,0.002823216,0.0003761246],"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":[0.002436995,0.000590097,0.006338551,0.0006675614,0.0001357112,0.000614814,0.0003434785,0.03976937,0.1161307,0.04946943,0.01467954,0.7688237],"study_design_scores_gemma":[0.0001902147,0.0004155131,0.001907716,0.00011664,0.00008368479,0.002538231,0.0002977426,0.7554786,0.1477016,0.08075094,0.01043964,0.00007955113],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07024372,0.001245519,0.9128219,0.001219926,0.0002799777,0.0002290841,0.0002594318,0.003506273,0.01019415],"genre_scores_gemma":[0.6255075,0.0006926962,0.3652866,0.0002878141,0.0001822311,0.0001257803,0.0004653825,0.0003227252,0.007129338],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01206427,"threshold_uncertainty_score":0.04035902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04351096778690593,"score_gpt":0.3783818313598122,"score_spread":0.3348708635729063,"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."}}