{"id":"W3092501099","doi":"10.48550/arxiv.2010.05844","title":"Conditioning Trick for Training Stable GANs","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Truncation (statistics); Generator (circuit theory); Normality; Spectrogram; Noise (video); Decomposition; Fidelity; Margin (machine learning); Residual; Artificial intelligence; Variety (cybernetics); SIGNAL (programming language); Function (biology); Algorithm; Speech recognition; Machine learning; Mathematics; Image (mathematics); Power (physics); Telecommunications","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":[0.0001902483,0.0002381667,0.0003326055,0.0001425904,0.0003212206,0.0002612308,0.001208526,0.000173047,0.00003866474],"category_scores_gemma":[0.00005893023,0.0002917568,0.0001917511,0.0004770843,0.00005980394,0.0004683663,0.0007801864,0.0003865557,0.00002589931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001097974,"about_ca_system_score_gemma":0.0004320644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001686769,"about_ca_topic_score_gemma":0.000003539312,"domain_scores_codex":[0.998354,0.00004615953,0.0001781956,0.0009791541,0.00007320293,0.0003692585],"domain_scores_gemma":[0.998844,0.0001371099,0.0002609699,0.0004671417,0.000124595,0.000166142],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005816298,0.00009533562,0.0003649391,0.0007615454,0.000255092,0.0003939786,0.006477221,0.2045625,0.0005199364,0.7669721,0.01028444,0.009254721],"study_design_scores_gemma":[0.0008315531,0.00005580778,0.00007883445,0.0001896731,0.00006915831,0.000004173094,0.0003806495,0.8228226,0.0005946771,0.1657346,0.008658214,0.0005801112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01456296,0.00004878465,0.9774757,0.0005919446,0.0004595807,0.0002617248,0.00002667944,0.0003186076,0.006254014],"genre_scores_gemma":[0.9816474,0.00001917917,0.01601981,0.0007097042,0.0001728851,0.000002293635,0.00003190461,0.00001872809,0.001378081],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9670845,"threshold_uncertainty_score":0.9999534,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1923668003268079,"score_gpt":0.2068957736358298,"score_spread":0.01452897330902192,"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."}}