{"id":"W3110500283","doi":"10.48550/arxiv.2004.04795","title":"Exemplar VAE: Linking Generative Models, Nearest Neighbor Retrieval, and\\n Data Augmentation","year":2020,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"MNIST database; Generative model; Artificial intelligence; Computer science; Pattern recognition (psychology); k-nearest neighbors algorithm; Estimator; Nearest neighbor search; Generative grammar; Mathematics; Artificial neural network; Statistics","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","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008360265,0.001008274,0.001001797,0.0002817103,0.001197098,0.001275485,0.004446996,0.0005964811,0.0001167118],"category_scores_gemma":[0.0001545271,0.001213397,0.0002528985,0.001529114,0.0004663242,0.004067107,0.01139088,0.001318519,0.00009221351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003210899,"about_ca_system_score_gemma":0.0007127746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004218893,"about_ca_topic_score_gemma":0.0001030151,"domain_scores_codex":[0.9923674,0.001020055,0.000711231,0.004688749,0.0003545644,0.0008579617],"domain_scores_gemma":[0.9943424,0.0003835687,0.0008653518,0.003221912,0.0005149412,0.0006717888],"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":[0.0004133705,0.0001372682,0.0002542364,0.0001387008,0.0005326596,0.0005065582,0.001808089,0.9612098,0.0008308188,0.02941673,0.00130063,0.003451165],"study_design_scores_gemma":[0.001150986,0.0001941633,0.0002527545,0.000253553,0.0004779744,0.000008678007,0.000350556,0.9700348,0.0007980681,0.02400503,0.001321751,0.001151636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01267512,0.0007373168,0.9815565,0.001157659,0.001516987,0.0009429749,0.0003133441,0.0001704243,0.0009297147],"genre_scores_gemma":[0.9666591,0.00509977,0.02558088,0.0005820097,0.0008861197,0.000001102606,0.0005339032,0.00006741506,0.0005897011],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9559756,"threshold_uncertainty_score":0.9997613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2224655351110088,"score_gpt":0.2311056769498889,"score_spread":0.008640141838880094,"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."}}