{"id":"W2964250748","doi":"","title":"Yes, but did it work?: Evaluating variational inference","year":2018,"lang":"en","type":"article","venue":"Aaltodoc (Aalto University)","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Office of Naval Research; National Science Foundation","keywords":"Inference; Pareto principle; Computer science; Calibration; Sampling (signal processing); Mathematical optimization; Point (geometry); Sampling distribution; Algorithm; Work (physics); Applied mathematics; Mathematics; Artificial intelligence; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000625783,0.0001868252,0.000260639,0.0001729679,0.0003012295,0.0000494222,0.0003986739,0.0001143169,0.002847841],"category_scores_gemma":[0.003729176,0.0001904662,0.00006930649,0.0006421226,0.0002142451,0.0001844675,0.0002137281,0.0002198598,0.0003953979],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00012592,"about_ca_system_score_gemma":0.0002057687,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007865316,"about_ca_topic_score_gemma":0.00004093172,"domain_scores_codex":[0.998324,0.0002852335,0.0002616566,0.0003736878,0.0003895636,0.0003657987],"domain_scores_gemma":[0.9964584,0.002396321,0.000176801,0.0003641237,0.0004315402,0.0001728361],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006839482,0.0000807364,0.001450177,0.0000299894,0.00004326964,0.00002030247,0.0004320614,0.000002735099,0.0002934102,0.9776257,0.003374049,0.01657913],"study_design_scores_gemma":[0.00238276,0.001154407,0.02585494,0.0004952656,0.0003731947,0.00001613574,0.001068878,0.008053271,0.001039124,0.855017,0.1031717,0.001373382],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09448643,0.00001518283,0.7267506,0.000750341,0.0005180617,0.0003365336,0.00005747532,0.0002090862,0.1768763],"genre_scores_gemma":[0.4067088,0.00001763907,0.5791563,0.0004029421,0.0003528673,0.000001927732,0.000009438187,0.00002729649,0.01332275],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3122224,"threshold_uncertainty_score":0.9980637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1916885171313321,"score_gpt":0.399855185023395,"score_spread":0.2081666678920628,"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."}}