{"id":"W3092636093","doi":"10.48550/arxiv.2010.03172","title":"Improving Sequential Latent Variable Models with Autoregressive Flows","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Autoregressive model; STAR model; Computer science; Latent variable; Generalization; Benchmark (surveying); Decorrelation; Sequence (biology); Latent variable model; Nonlinear autoregressive exogenous model; Flow (mathematics); Algorithm; Mathematics; Artificial intelligence; Econometrics; Machine learning; Time series; Autoregressive integrated moving average","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003287867,0.001728303,0.001504457,0.001630823,0.0004839222,0.00138785,0.001999644,0.001140121,0.002101757],"category_scores_gemma":[0.008834331,0.0009072765,0.001698688,0.001632633,0.0007160819,0.003830876,0.001608524,0.002710221,0.00140318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001099749,"about_ca_system_score_gemma":0.001871988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01172883,"about_ca_topic_score_gemma":0.01241654,"domain_scores_codex":[0.9985241,0.0005647859,0.00007652138,0.000427499,0.000286792,0.0001203598],"domain_scores_gemma":[0.9972801,0.001627346,0.0002903331,0.0004229215,0.0003024771,0.00007687708],"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":[0.0001417505,0.0001561738,0.002167137,0.0001105231,0.0001738344,0.0001125277,0.0002071332,0.7142947,0.005892582,0.04042143,0.003612458,0.2327096],"study_design_scores_gemma":[0.000004412555,0.00001779113,0.0001227066,0.000006942076,0.000009092819,0.00001147685,0.000005914903,0.9875328,0.0006395743,0.01088875,0.0007519934,0.000008629014],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005548371,0.000175542,0.9931536,0.00009854688,0.00003070912,0.00001768424,0.0001023427,0.0005814335,0.0002919291],"genre_scores_gemma":[0.3670239,0.001109545,0.6211131,0.000331659,0.0002896406,0.000327826,0.002702708,0.0006228457,0.006478735],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01172883,"threshold_uncertainty_score":0.02332109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08801303252900683,"score_gpt":0.1775962548276962,"score_spread":0.08958322229868934,"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."}}