{"id":"W7115590573","doi":"10.1051/itmconf/20258001029","title":"An Investigation of Face Generation Methods Based on Encoders, GAN and Diffusion models","year":2025,"lang":"en","type":"article","venue":"ITM Web of Conferences","topic":"Face recognition and analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Bridging (networking); Generative grammar; Face (sociological concept); Tracing; Key (lock); Natural language generation; Adversarial system","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":[0.002473337,0.0007443179,0.0005857702,0.0005270507,0.0002689999,0.001032319,0.00101564,0.0009654408,0.002464838],"category_scores_gemma":[0.005867093,0.0005069625,0.0007832976,0.0003516135,0.001007138,0.001774313,0.0009245335,0.001918943,0.0007618919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007419438,"about_ca_system_score_gemma":0.0005390443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001823041,"about_ca_topic_score_gemma":0.001597242,"domain_scores_codex":[0.9992672,0.0002934287,0.00003035861,0.0001723643,0.0001961901,0.00004043126],"domain_scores_gemma":[0.9978094,0.001731838,0.00007817916,0.0001688238,0.0001758656,0.00003597149],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001109389,0.00006818119,0.001917098,0.0007092935,0.0001543394,0.0001494403,0.0003521776,0.3682406,0.0104341,0.1986311,0.003332507,0.4159003],"study_design_scores_gemma":[0.00001034675,0.00008768431,0.0005020018,0.0001162766,0.00003291836,0.0002799761,0.000039778,0.9464107,0.005090535,0.03882539,0.008577781,0.0000265403],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008681063,0.008609608,0.9738299,0.0007655656,0.0001622803,0.00006046116,0.00005500543,0.0002664412,0.007569677],"genre_scores_gemma":[0.5874671,0.02052984,0.3756978,0.0007288124,0.0004569431,0.0002536937,0.0002887962,0.0003732403,0.01420375],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002473337,"threshold_uncertainty_score":0.01308042,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05599798741465727,"score_gpt":0.3249873879777418,"score_spread":0.2689894005630846,"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."}}