{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00009142329,0.0002920827,0.0002789198,0.0001624447,0.0001978548,0.0002540492,0.0009736393,0.0002147767,0.00006526496],"category_scores_gemma":[0.000006622599,0.0002982425,0.0001260823,0.0002949463,0.00004472463,0.0008382548,0.001178674,0.0005932509,0.00009644271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001846169,"about_ca_system_score_gemma":0.0003755363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002506129,"about_ca_topic_score_gemma":0.0000276261,"domain_scores_codex":[0.998248,0.00008849501,0.0001599141,0.001079975,0.0001203868,0.0003031994],"domain_scores_gemma":[0.9986683,0.00002708421,0.0002801572,0.0006365299,0.0001923545,0.0001956396],"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":[0.00005649987,0.0000804907,0.00006009499,0.0001285462,0.000184781,0.0008186537,0.000376544,0.8170847,0.0003835773,0.1794037,0.0002272136,0.001195221],"study_design_scores_gemma":[0.0004323246,0.00006391574,0.00002292074,0.0001060696,0.00008598413,0.000008758449,0.00001857353,0.9353046,0.0003503106,0.0631094,0.0001294911,0.0003676556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0453652,0.00001466667,0.9500521,0.00008375369,0.0004684163,0.0002708807,0.00002093339,0.0004106067,0.003313378],"genre_scores_gemma":[0.9860338,0.00002454109,0.01274177,0.0001547022,0.0001501856,0.000002091404,0.00003963723,0.00002056561,0.0008327118],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9406686,"threshold_uncertainty_score":0.999947,"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."}}