{"id":"W2950339535","doi":"10.48550/arxiv.1806.03968","title":"CapsGAN: Using Dynamic Routing for Generative Adversarial Networks","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; MNIST database; Normalization (sociology); Artificial intelligence; Knot (papermaking); Image translation; Algorithm; Clipping (morphology); Computer vision; Image (mathematics); Deep learning","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":[0.0004994992,0.0005723925,0.0006073732,0.0002095547,0.0006731357,0.0003376522,0.001817462,0.000511771,0.00002532277],"category_scores_gemma":[0.00008760724,0.0006524538,0.0004703126,0.0005278603,0.0002153832,0.0006023531,0.002126842,0.0005153535,0.00001456378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004887416,"about_ca_system_score_gemma":0.0003722581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001936906,"about_ca_topic_score_gemma":0.0001169111,"domain_scores_codex":[0.9967209,0.0003055306,0.0003572916,0.001755684,0.0001061371,0.0007544718],"domain_scores_gemma":[0.9973606,0.0002229381,0.0005236082,0.001197481,0.000482988,0.0002123799],"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":[0.00005087767,0.00004039057,0.00006618434,0.00001845302,0.0002087757,0.00004238623,0.0001979532,0.9888924,0.0001519406,0.009186893,0.0004429139,0.0007008371],"study_design_scores_gemma":[0.0006869226,0.00008531388,0.00003801092,0.00009165688,0.0001727111,0.000003533626,0.00005860975,0.9896491,0.0003797933,0.007885396,0.0002481725,0.0007008114],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01768355,0.00009596365,0.9771973,0.00007343201,0.00363207,0.0007400062,0.00003214234,0.0001869071,0.0003585711],"genre_scores_gemma":[0.9284532,0.00006100796,0.06949434,0.0001406567,0.001279455,0.000002898782,0.00004313043,0.00004423065,0.0004810714],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9107696,"threshold_uncertainty_score":0.9995927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07079669769047088,"score_gpt":0.2088384478779232,"score_spread":0.1380417501874524,"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."}}