{"id":"W1859551169","doi":"10.48550/arxiv.1708.00805","title":"Variational Generative Stochastic Networks with Collaborative Shaping","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"MNIST database; Computer science; Generative grammar; Generative model; Artificial intelligence; Regularization (linguistics); Reinforcement learning; Machine learning; Autoencoder; Markov chain; Bayesian probability; Mathematical optimization; Artificial neural network; Mathematics","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":[0.0001744311,0.0002016758,0.0002007786,0.00007021487,0.001254564,0.0004372073,0.001061299,0.00007046019,0.00003387897],"category_scores_gemma":[0.00005994929,0.0001874187,0.00005486193,0.0003320329,0.0001973323,0.001464275,0.0003148762,0.0001501993,0.00002566111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008151791,"about_ca_system_score_gemma":0.000156223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004776801,"about_ca_topic_score_gemma":0.0001013237,"domain_scores_codex":[0.9987495,0.000117108,0.0001075392,0.0006257712,0.00009073307,0.000309378],"domain_scores_gemma":[0.9984,0.0001201338,0.0002524355,0.000759154,0.0003340355,0.0001342628],"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":[0.00003119907,0.00002635521,0.0004570687,8.353144e-7,0.00007502473,0.00006160009,0.0001381983,0.8628846,0.00003101512,0.1356844,0.0001805478,0.0004291194],"study_design_scores_gemma":[0.0006071076,0.00009309341,0.003617821,0.00002055661,0.00002819393,0.000003333879,0.00006176395,0.9922488,0.00008009177,0.002864185,0.0001132086,0.0002618487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004487595,0.00002937608,0.9922521,0.0002933186,0.0002568876,0.0001815924,0.000005264366,0.00006457887,0.002429338],"genre_scores_gemma":[0.981976,0.00001336149,0.01700025,0.0001436945,0.0002027943,0.000001425434,0.000003504376,0.00001040874,0.000648614],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9774883,"threshold_uncertainty_score":0.9649215,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05326528497967509,"score_gpt":0.1830332014202123,"score_spread":0.1297679164405372,"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."}}