{"id":"W3214044012","doi":"","title":"Efficient Density Ratio-Guided Subsampling of Conditional GANs, With Conditioning on a Class or a Continuous Variable.","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Sampling (signal processing); AKA; Benchmark (surveying); Conditional probability distribution; Artificial intelligence; Margin (machine learning); Pattern recognition (psychology); Statistics; Mathematics; Algorithm; Machine learning; Computer vision","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":[0.000315568,0.0003582155,0.0005869609,0.0002011633,0.0002862766,0.0002025526,0.0007221128,0.0002127276,0.0001206111],"category_scores_gemma":[0.00009901811,0.0003388701,0.0001676939,0.0006779075,0.0002093288,0.0001696471,0.0006185879,0.0004495046,0.000008099142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001874141,"about_ca_system_score_gemma":0.0007171125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001321879,"about_ca_topic_score_gemma":0.00005751337,"domain_scores_codex":[0.9977267,0.0002932519,0.0003170166,0.001109922,0.000209539,0.0003435511],"domain_scores_gemma":[0.997369,0.0004310024,0.000483692,0.0008328109,0.0007409671,0.0001425263],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001286082,0.0001626528,0.0003673577,0.00004733228,0.0002061743,0.0003608162,0.000166738,0.9284174,0.0005308118,0.06942264,0.00016028,0.00002916259],"study_design_scores_gemma":[0.00099053,0.0001657488,0.001209361,0.0004101144,0.0001397788,0.00002493431,0.0002359937,0.9906303,0.003835053,0.001847732,0.00004030728,0.0004701949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2752897,0.00001400061,0.7235847,0.00004794514,0.0002520785,0.0002584108,0.00003900451,0.0000678794,0.0004462962],"genre_scores_gemma":[0.9804962,0.00001311261,0.01878659,0.0001746351,0.00008778493,0.000002504796,0.0001108087,0.000017999,0.0003103837],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7052065,"threshold_uncertainty_score":0.9999064,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05554160688820715,"score_gpt":0.1924213441874704,"score_spread":0.1368797372992632,"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."}}