{"id":"W1811734137","doi":"10.48550/arxiv.1211.4246","title":"What Regularized Auto-Encoders Learn from the Data Generating Distribution","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":101,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Encoder; Algorithm; Computer science; Autoencoder; Parametrization (atmospheric modeling); Function (biology); Probability density function; Mathematics; Pattern recognition (psychology); Artificial intelligence; Applied mathematics; Statistics; 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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007614514,0.0003778609,0.0003565756,0.00003954564,0.0005769731,0.001041697,0.004693281,0.0002972976,0.00005508014],"category_scores_gemma":[0.0001375243,0.0003281494,0.0001802543,0.0003920831,0.0001734594,0.002664085,0.006989187,0.0007160942,0.00007456922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001698213,"about_ca_system_score_gemma":0.0002068284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007704429,"about_ca_topic_score_gemma":0.0001340632,"domain_scores_codex":[0.996988,0.0006710485,0.0002545789,0.001435423,0.0001630288,0.0004879373],"domain_scores_gemma":[0.9953064,0.0003536365,0.0003647502,0.003660667,0.000152914,0.0001616575],"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":[0.00004717315,0.0001533489,0.001075719,0.00002427473,0.0005809175,0.0000982729,0.001344542,0.9371871,0.0009347564,0.0199422,0.01612111,0.02249052],"study_design_scores_gemma":[0.0002684607,0.000008584654,0.0005212997,0.000088008,0.0001431774,0.000001198736,0.000233033,0.9873275,0.0001557646,0.004623193,0.006234491,0.0003953587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01361919,0.0006868323,0.9811004,0.0009654269,0.002885674,0.0002970815,0.0001694664,0.0001654668,0.0001104051],"genre_scores_gemma":[0.9852458,0.0008234141,0.01094353,0.0002527729,0.000872681,0.000001189468,0.001141221,0.00002037684,0.0006990226],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9716266,"threshold_uncertainty_score":0.9999953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1121704691658807,"score_gpt":0.2034942332074061,"score_spread":0.09132376404152547,"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."}}