{"id":"W2123284177","doi":"10.48550/arxiv.1206.6434","title":"A Generative Process for Sampling Contractive Auto-Encoders","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Jacobian matrix and determinant; Representation (politics); Encoder; Manifold (fluid mechanics); Generative model; Computer science; Generative grammar; Algorithm; Invariant (physics); Boltzmann machine; Mathematics; Transformation (genetics); Artificial intelligence; Pattern recognition (psychology); Applied 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":[],"consensus_categories":[],"category_scores_codex":[0.0002569414,0.0001798568,0.0001946278,0.00008524493,0.0003312464,0.0000711096,0.0004954754,0.00007586033,0.00001691911],"category_scores_gemma":[0.00008345365,0.0001827989,0.0001193169,0.0004147655,0.00007218738,0.001706592,0.00009363514,0.0001089976,0.00002446504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009059266,"about_ca_system_score_gemma":0.00008030417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001782299,"about_ca_topic_score_gemma":0.000009037763,"domain_scores_codex":[0.9988018,0.00008621114,0.0001173363,0.0004532693,0.00005871936,0.0004826859],"domain_scores_gemma":[0.9989394,0.0002481292,0.0001212954,0.0003008095,0.0002089266,0.0001814508],"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":[0.000138531,0.0003534608,0.002760141,0.00003060929,0.0002923261,0.00001743342,0.003855325,0.6044669,0.002971039,0.3792836,0.0007463659,0.005084293],"study_design_scores_gemma":[0.000670395,0.00007626666,0.0005978066,0.00001307978,0.00004595423,0.00000298797,0.0005209532,0.9787961,0.005874196,0.01126254,0.001801055,0.0003387304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0303497,0.00006137935,0.9675592,0.0001434059,0.0003752675,0.0003134212,0.000007619225,0.00009381879,0.001096238],"genre_scores_gemma":[0.9826856,0.00001297394,0.01641805,0.0002256557,0.0002371801,0.000004006075,0.000003261824,0.00001132731,0.0004019364],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9523359,"threshold_uncertainty_score":0.7454323,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1173391850813718,"score_gpt":0.2263930692046549,"score_spread":0.1090538841232831,"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."}}