{"id":"W4416028058","doi":"10.1038/s40494-025-02100-3","title":"Hierarchical symmetric GAN for Thangka image generation","year":2025,"lang":"en","type":"article","venue":"npj Heritage Science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Overfitting; Discriminator; Feature (linguistics); Pattern recognition (psychology); Image (mathematics); Generalization; Object (grammar); Differentiable function; Generator (circuit theory)","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":[0.001057661,0.000153603,0.0001706398,0.0003846223,0.000722399,0.0007362644,0.001424005,0.0000522164,0.00001382324],"category_scores_gemma":[0.0005802659,0.0001360701,0.00008873158,0.002838967,0.0003721422,0.001320246,0.000257139,0.0001111548,0.0000189586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008774376,"about_ca_system_score_gemma":0.0003289188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001056574,"about_ca_topic_score_gemma":0.00001187653,"domain_scores_codex":[0.9981067,0.00006557853,0.0002295326,0.0007264331,0.0003714296,0.0005003161],"domain_scores_gemma":[0.9987663,0.0001605873,0.00006081846,0.0005978079,0.0002919769,0.0001224915],"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":[0.00001018955,0.0001473699,0.0001696864,0.00002776448,0.0000168746,0.000008350518,0.0004572072,0.0007745645,0.5909513,0.2229131,0.01338345,0.1711402],"study_design_scores_gemma":[0.0003511066,0.0001137433,0.001403829,0.00001820138,0.000008764316,0.000002901573,0.00004674639,0.8517749,0.1327897,0.004969349,0.008263947,0.0002567317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003495411,0.0001561024,0.978995,0.002136719,0.001201063,0.0003412778,0.000004198164,0.0001023743,0.01356785],"genre_scores_gemma":[0.7455394,0.00001210341,0.2525622,0.00074291,0.0002045858,0.00004650844,0.000001789206,0.000005163199,0.0008854216],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8510004,"threshold_uncertainty_score":0.7099814,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01952224426569896,"score_gpt":0.2767312467106408,"score_spread":0.2572090024449418,"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."}}