{"id":"W2964005169","doi":"","title":"Bounding the Test Log-Likelihood of Generative Models","year":2014,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Canadian Institute for Advanced Research","funders":"","keywords":"Estimator; Normalization (sociology); Mathematics; Random variable; Bounding overwatch; Probability density function; Applied mathematics; Upper and lower bounds; Generative model; Algorithm; Latent variable; Computer science; Statistics; Artificial intelligence; Generative grammar","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":[0.0002260014,0.00009659296,0.0001144896,0.00005721483,0.0002181911,0.00005038965,0.001017582,0.00003990041,0.000007539451],"category_scores_gemma":[0.0000372509,0.00007288436,0.00005374087,0.0003697479,0.00008456747,0.0006437102,0.0004611671,0.0000983417,0.00001965546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000262261,"about_ca_system_score_gemma":0.00003681741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006134081,"about_ca_topic_score_gemma":0.00001287191,"domain_scores_codex":[0.999249,0.00007803038,0.00009580132,0.0003231798,0.00006843516,0.0001855459],"domain_scores_gemma":[0.9988657,0.0002504265,0.00009835132,0.00064069,0.00008001814,0.00006477223],"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":[0.000005840436,0.00008467071,0.001060825,0.000006939807,0.00001744957,0.00001316045,0.0004257349,0.05752143,0.0009334677,0.9347018,0.0007023611,0.004526315],"study_design_scores_gemma":[0.0002000245,0.00005686187,0.000343295,0.00001208019,0.000007938604,0.000001983981,0.0000435629,0.9049426,0.0009094205,0.09281159,0.000578298,0.00009233254],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05471269,0.0000186593,0.9417726,0.00009887187,0.0001303476,0.0000642677,0.000004377584,0.00004726859,0.003150943],"genre_scores_gemma":[0.9934632,0.00002142701,0.006119889,0.0001014605,0.00004518859,1.885256e-7,0.000001561101,0.000004258073,0.0002428362],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9387505,"threshold_uncertainty_score":0.2972138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05407829582841282,"score_gpt":0.1740231981928927,"score_spread":0.1199449023644798,"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."}}