mlsanityData to 14 Oct 2026

MASCIT: A Mask-Aware State Space Classifier for Naturally Irregular Time Series

arXiv 2609.34409 ↗First posted 28 Sep 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Naturally irregular time series combine asynchronous observations, missing values, unequal lengths, and nonuniform sampling, while dense adapters can discard temporal structure. We propose a mask-aware state space classifier for irregular time series (MASCIT), which supplies observation masks to the encoder and excludes invalid steps from gated temporal aggregation. Across 34 irregular time series datasets, MASCIT yielded the strongest aggregate point estimate and was the only evaluated neural model with three-seed results on every dataset. MASCIT retained the lowest point rank across six overlapping irregularity indicators, while factorial ablations favored partial over full selectivity. These results support selective state space models as effective, executable backbones for naturally irregular time series classification.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 25 references that are in the map. First posted on arXiv 28 Sep 2026.

Builds on

14 of 25 references.

References · 14

  1. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  2. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  3. 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 608
  4. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 554
  5. 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 506
  6. 2019ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernelscited by 339
  7. 2018BRITS: Bidirectional Recurrent Imputation for Time Seriescited by 290
  8. 2021Multi-Time Attention Networks for Irregularly Sampled Time Seriescited by 238
  9. 2020MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classificationcited by 190
  10. 2022SAITS: Self-Attention-based Imputation for Time Seriescited by 169
  11. 2020Benchmarking Multivariate Time Series Classification Algorithmscited by 145
  12. 2023Fast, Interpretable, and Deterministic Time Series Classification With a Bag-of-Receptive-Fieldscited by 8
2 more
  1. 2025PYRREGULAR: A Unified Framework for Irregular Time Series, with Classification Benchmarkscited by 7
  2. 2026MambaSL: Exploring Single-Layer Mamba for Time Series Classificationcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025A Diffusion Model for Regular Time Series Generation from Irregular Data with Completion and Masking
  2. 2026Reshape and Recur: Improving SSMs with Input Reshaping and Depth Recurrence
  3. 2023Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series
  4. 2023Effectively Modeling Time Series with Simple Discrete State Spaces
  5. 2026LogSig-SSM: Time-Series Modelling with Multi-Scale Log-Signature Compression for State-Space Models
  6. 2026A Simple State Space Model Excels at Multivariate Time Series Classification
  7. 2026TIDES: Implicit Time-Awareness in Selective State Space Models
  8. 2026Enhancing Irregular Time Series Forecasting with Continuous-Time Modeling Framework