{"id":"W3174139848","doi":"10.1609/aaai.v35i9.16967","title":"IB-GAN: Disentangled Representation Learning with Information Bottleneck Generative Adversarial Networks","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Defense Acquisition Program Administration; Agency for Defense Development","keywords":"Representation (politics); Bottleneck; Generator (circuit theory); Computer science; Information bottleneck method; Layer (electronics); Generative grammar; Artificial intelligence; Quality (philosophy); Space (punctuation); Mutual information; Power (physics); Materials science","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":[0.0002957174,0.0002292055,0.0002694289,0.00008070426,0.0003707945,0.0005416019,0.0007801183,0.00008585998,0.00006536172],"category_scores_gemma":[0.0004478748,0.000167409,0.0001135263,0.0009198543,0.0001775466,0.00152717,0.0002585352,0.0003317597,0.00002896786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005446454,"about_ca_system_score_gemma":0.0001489245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003555658,"about_ca_topic_score_gemma":0.00002190539,"domain_scores_codex":[0.99818,0.0000710362,0.0004955384,0.0004237157,0.0005135965,0.0003161334],"domain_scores_gemma":[0.9978329,0.0001133248,0.0004762832,0.000265847,0.001225671,0.00008595503],"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":[0.0004024035,0.0002232912,0.001292662,0.00003568599,0.0001417659,0.000004915986,0.0055068,0.1977672,0.03620306,0.5903208,0.0006401333,0.1674613],"study_design_scores_gemma":[0.00006925251,0.0001527049,0.0002305071,0.0001002142,0.00002135463,0.000005910608,0.001185948,0.5572919,0.4335772,0.007005924,0.0001597775,0.0001993791],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02153031,0.00002727534,0.9637409,0.003364764,0.0006797697,0.0003908589,0.000002996044,0.00008772525,0.01017536],"genre_scores_gemma":[0.989066,0.00005957983,0.01019462,0.000241913,0.0001953524,0.00002512904,0.00000538462,0.000009546521,0.0002024604],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9675357,"threshold_uncertainty_score":0.6826739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03291350523931318,"score_gpt":0.2531786174233732,"score_spread":0.22026511218406,"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."}}