{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003309232,0.00007085937,0.0001522177,0.0002206155,0.00004558946,0.00005154191,0.000186544,0.00004635104,0.00001287295],"category_scores_gemma":[0.00002533707,0.00005978642,0.00003087375,0.0002750482,0.00007033274,0.0002484279,0.0000185168,0.00003986658,3.246543e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005088974,"about_ca_system_score_gemma":0.0002984538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006796372,"about_ca_topic_score_gemma":0.00004203026,"domain_scores_codex":[0.9991867,0.0002178444,0.0001930888,0.0001938303,0.0001477681,0.00006079109],"domain_scores_gemma":[0.9994358,0.0001027227,0.0001069845,0.0001819548,0.0001336483,0.00003884899],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001235688,0.0001214967,0.006212081,0.00007929838,0.00003588678,3.273841e-7,0.001039344,0.01972789,0.5010597,0.1661217,0.0001070032,0.305483],"study_design_scores_gemma":[0.0001397007,0.0000653723,0.0008579571,0.00004418492,0.00001103099,5.161508e-8,0.00009694301,0.8419141,0.1477914,0.009010869,0.00001955984,0.00004884072],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.218063,0.00003861157,0.7790806,0.0007222348,0.00004394514,0.00005531501,0.000002389562,0.00001909197,0.00197481],"genre_scores_gemma":[0.9432796,0.00004272357,0.05644444,0.0001825672,0.000005227863,0.000003708043,0.000009304365,0.000001181937,0.00003120404],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8221862,"threshold_uncertainty_score":0.243802,"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."}}