{"url":"/sota/multivariate-time-series-imputation-on","task":{"name":"Multivariate Time Series Imputation","url":"/task/multivariate-time-series-imputation","note":null},"dataset":{"name":"Beijing Multi-Site Air-Quality Dataset","url":"/dataset/beijing-air-quality"},"category":"Computer Vision","categories":["Computer Vision","Time Series"],"category_note":null,"description":null,"description_from":null,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["MAE (PM2.5)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"MAE (PM2.5)":"lower"}},"counts":{"rows":6,"rows_with_code":5,"rows_with_paper_page":6,"rows_dated":6,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"GRIN","metrics":{"MAE (PM2.5)":"10.51"},"uses_additional_data":false,"paper_date":"2021-07-31","paper":"/paper/multivariate-time-series-imputation-by-graph","paper_url":"https://arxiv.org/abs/2108.00298v3","paper_title":"Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networks","code":"https://github.com/torchspatiotemporal/tsl","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":5,"n_samples":10,"n_pointer_only_licence":9}},{"rank_in_archive_order":2,"model":"BRITS","metrics":{"MAE (PM2.5)":"11.56"},"uses_additional_data":false,"paper_date":"2018-05-27","paper":"/paper/brits-bidirectional-recurrent-imputation-for","paper_url":"http://arxiv.org/abs/1805.10572v1","paper_title":"BRITS: Bidirectional Recurrent Imputation for Time Series","code":"https://github.com/WenjieDu/PyPOTS","n_code_links":5,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"STMVL","metrics":{"MAE (PM2.5)":"12.12"},"uses_additional_data":false,"paper_date":"2016-07-09","paper":"/paper/st-mvl-filling-missing-values-in-geo-sensory","paper_url":"https://www.microsoft.com/en-us/research/publication/st-mvl-filling-missing-values-in-geo-sensory-time-series-data/","paper_title":"ST-MVL: Filling Missing Values in Geo-Sensory Time Series Data","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"M-RNN","metrics":{"MAE (PM2.5)":"14.24"},"uses_additional_data":false,"paper_date":"2017-11-23","paper":"/paper/estimating-missing-data-in-temporal-data","paper_url":"http://arxiv.org/abs/1711.08742v1","paper_title":"Estimating Missing Data in Temporal Data Streams Using Multi-directional Recurrent Neural Networks","code":"https://github.com/WenjieDu/PyPOTS","n_code_links":3,"syntology":null},{"rank_in_archive_order":5,"model":"ImputeTS","metrics":{"MAE (PM2.5)":"19.58"},"uses_additional_data":false,"paper_date":"2017-06-01","paper":"/paper/imputets-time-series-missing-value-imputation","paper_url":"http://doi.org/10.32614/RJ-2017-009","paper_title":"imputeTS: Time Series Missing Value Imputation in R","code":"https://github.com/SteffenMoritz/imputeTS","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"MICE","metrics":{"MAE (PM2.5)":"27.42"},"uses_additional_data":false,"paper_date":"2010-11-30","paper":"/paper/multiple-imputation-using-chained-equations","paper_url":"https://doi.org/10.1002/sim.4067","paper_title":"Multiple imputation using chained equations: issues and guidance for practice","code":"https://github.com/stefvanbuuren/mice","n_code_links":1,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":2,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":7,"n_unverified":7,"n_samples":14,"n_pointer_only_licence":9,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":7,"n_unverified":7,"n_samples":14,"n_pointer_only_licence":9,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}