Pith. sign in

REVIEW 3 cited by

Mamba4Cast: Efficient Zero-Shot Time Series Forecasting with State Space Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.09385 v1 pith:KTVXYSAK submitted 2024-10-12 cs.LG cs.AI

Sathya Kamesh Bhethanabhotla , Omar Swelam , Julien Siems , David Salinas , Frank Hutter This is my paper · ORCID
classification cs.LGcs.AI
keywords mamba4castseriestimefoundationmodelszero-shotarchitecturedata
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper introduces Mamba4Cast, a zero-shot foundation model for time series forecasting. Based on the Mamba architecture and inspired by Prior-data Fitted Networks (PFNs), Mamba4Cast generalizes robustly across diverse time series tasks without the need for dataset specific fine-tuning. Mamba4Cast's key innovation lies in its ability to achieve strong zero-shot performance on real-world datasets while having much lower inference times than time series foundation models based on the transformer architecture. Trained solely on synthetic data, the model generates forecasts for entire horizons in a single pass, outpacing traditional auto-regressive approaches. Our experiments show that Mamba4Cast performs competitively against other state-of-the-art foundation models in various data sets while scaling significantly better with the prediction length. The source code can be accessed at https://github.com/automl/Mamba4Cast.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Time Series Representations for Classification Lie Hidden in Pretrained Vision Transformers

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Frozen vision transformers, applied to image representations of time series, produce classification features that outperform or match time series foundation models on UCR and UEA benchmarks.

  2. A Minimal Interpretable Architecture for Zero-Shot Reconstruction of Dynamical Systems

    cs.LG 2026-07 conditional novelty 5.0 of 10

    A two-parameter nearest-neighbor recurrence, DynaBase, matches large foundation models at zero-shot dynamical-system reconstruction and unifies context parroting with chaotic dynamics as two ends of one parameter.

  3. Scaling Law for Large-Scale Pre-Training Using Chaotic Time Series and Predictability in Financial Time Series

    cs.LG 2025-09 reject novelty 5.0 of 10

    Pre-training on resampled Lorenz chaotic series yields zero-shot Bitcoin return predictions, with the training-sample count needed for a fixed skill level growing roughly exponentially with predictive horizon.

Pith tools