Impermanent: A Live Benchmark for Temporal Generalization in Time Series Forecasting

• URL: http://arxiv.org/abs/2603.08707v2
• Date: Tue, 10 Mar 2026 02:59:34 GMT
• Title: Impermanent: A Live Benchmark for Temporal Generalization in Time Series Forecasting
• Abstract summary: Impermanent is a live benchmark that evaluates forecasting models under open-world temporal change.<n>We focus on the top 400 repositories by star count and construct time series from issues opened, pull requests opened, push events, and new stargazers.<n>By shifting evaluation from static accuracy to sustained performance, Impermanent takes a concrete step toward assessing when and whether foundation-level generalization in time-series forecasting can be meaningfully claimed.
• Score: 8.050703449557028
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in time-series forecasting increasingly rely on pre-trained foundation-style models. While these models often claim broad generalization, existing evaluation protocols provide limited evidence. Indeed, most current benchmarks use static train-test splits that can easily lead to contamination as foundation models can inadvertently train on test data or perform model selection using test scores, which can inflate performance. We introduce Impermanent, a live benchmark that evaluates forecasting models under open-world temporal change by scoring forecasts sequentially over time on continuously updated data streams, enabling the study of temporal robustness, distributional shift, and performance stability rather than one-off accuracy on a frozen test set. Impermanent is instantiated on GitHub open-source activity, providing a naturally live and highly non-stationary dataset shaped by releases, shifting contributor behavior, platform/tooling changes, and external events. We focus on the top 400 repositories by star count and construct time series from issues opened, pull requests opened, push events, and new stargazers, evaluated over a rolling window with daily updates, alongside standardized protocols and leaderboards for reproducible, ongoing comparison. By shifting evaluation from static accuracy to sustained performance, Impermanent takes a concrete step toward assessing when and whether foundation-level generalization in time-series forecasting can be meaningfully claimed. Code and a live dashboard are available at https://github.com/TimeCopilot/impermanent and https://impermanent.timecopilot.dev.

Related papers

• LiveHouse-TS: An Open-world Living Benchmark for Time Series Foundation Models [41.28223590438589]
  We introduce LiveHouse-TS, the first open-world living benchmark infrastructure for Time Series Foundation Models.<n>LiveHouse-TS shifts time series benchmarking from snapshot accuracy to continuous temporal validity.<n>Our infrastructure serves as a continuous time series infrastructure designed to explore vital, long-term scientific questions.
  arXiv  Detail & Related papers  (2026-08-18T02:50:48Z)
• It's TIME: Towards the Next Generation of Time Series Forecasting Benchmarks [87.7937890373758]
  Time series foundation models (TSFMs) are revolutionizing the forecasting landscape from specific dataset modeling to generalizable task evaluation.<n>We introduce TIME, a next-generation task-centric benchmark comprising 50 fresh datasets and 98 forecasting tasks.<n>We propose a novel pattern-level evaluation perspective that moves beyond traditional dataset-level evaluations based on static meta labels.
  arXiv  Detail & Related papers  (2026-02-12T16:31:01Z)
• fev-bench: A Realistic Benchmark for Time Series Forecasting [19.931138737002215]
  Existing benchmarks often have narrow domain coverage or overlook important real-world settings.<n>We propose fevbench, a benchmark comprising 100 forecasting tasks across seven domains.<n> fev-bench employs principled aggregation methods with bootstrapped confidence intervals to report model performance.
  arXiv  Detail & Related papers  (2025-09-30T16:17:18Z)
• Estimating Time Series Foundation Model Transferability via In-Context Learning [74.65355820906355]
  Time series foundation models (TSFMs) offer strong zero-shot forecasting via large-scale pre-training.<n>Fine-tuning remains critical for boosting performance in domains with limited public data.<n>We introduce TimeTic, a transferability estimation framework that recasts model selection as an in-context-learning problem.
  arXiv  Detail & Related papers  (2025-09-28T07:07:13Z)
• Enhancing Transformer-Based Foundation Models for Time Series Forecasting via Bagging, Boosting and Statistical Ensembles [7.787518725874443]
  Time series foundation models (TSFMs) have shown strong generalization and zero-shot capabilities for time series forecasting, anomaly detection, classification, and imputation.<n>This paper investigates a suite of statistical and ensemble-based enhancement techniques to improve robustness and accuracy.
  arXiv  Detail & Related papers  (2025-08-18T04:06:26Z)
• Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting [64.45587649141842]
  Time-series forecasting plays a critical role in many real-world applications.<n>No single model consistently outperforms others across different test samples, but instead (ii) each model excels in specific cases.<n>We introduce TimeFuse, a framework for collective time-series forecasting with sample-level adaptive fusion of heterogeneous models.
  arXiv  Detail & Related papers  (2025-05-24T00:45:07Z)
• Sundial: A Family of Highly Capable Time Series Foundation Models [47.27032162475962]
  We introduce Sundial, a family of native, flexible, and scalable time series foundation models.<n>Our models are pre-trained without specifying any prior distribution and can generate multiple probable predictions.<n>Sundial achieves state-of-the-art results on both point and probabilistic forecasting benchmarks with a just-in-time inference speed.
  arXiv  Detail & Related papers  (2025-02-02T14:52:50Z)
• Battling the Non-stationarity in Time Series Forecasting via Test-time Adaptation [39.7344214193566]
  We introduce a pioneering test-time adaptation framework tailored for time series forecasting (TSF)<n>TAFAS, the proposed approach to TSF-TTA, flexibly adapts source forecasters to continuously shifting test distributions while preserving the core semantic information learned during pre-training.<n>The novel utilization of partially-observed ground truth and gated calibration module enables proactive, robust, and model-agnostic adaptation of source forecasters.
  arXiv  Detail & Related papers  (2025-01-09T04:59:15Z)
• Measuring Pre-training Data Quality without Labels for Time Series Foundation Models [10.64362760848387]
  We introduce contrastive accuracy, a new measure to evaluate the quality of the representation space learned by the foundation model.<n>Our experiments reveal the positive correlation between the proposed measure and the accuracy of the model on a collection of downstream tasks.
  arXiv  Detail & Related papers  (2024-12-09T10:38:30Z)
• Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization [74.3339999119713]
  We develop a wavelet-based tokenizer that allows models to learn complex representations directly in the space of time-localized frequencies.<n>Our method first scales and decomposes the input time series, then thresholds and quantizes the wavelet coefficients, and finally pre-trains an autoregressive model to forecast coefficients for the forecast horizon.
  arXiv  Detail & Related papers  (2024-12-06T18:22:59Z)
• DOTA: Distributional Test-Time Adaptation of Vision-Language Models [69.41389326333771]
  Vision-language foundation models can be unreliable when significant distribution gaps exist between training and test data.<n>We propose DOTA (DistributiOnal Test-time Adaptation), a simple yet effective method addressing this limitation.<n>This distribution-centric approach enables the model to continually learn and adapt to the deployment environment.
  arXiv  Detail & Related papers  (2024-09-28T15:03:28Z)
• FreDF: Learning to Forecast in the Frequency Domain [54.2091536822376]
  Time series modeling presents unique challenges due to autocorrelation in both historical data and future sequences.<n>We propose the Frequency-enhanced Direct Forecast (FreDF) which mitigates label autocorrelation by learning to forecast in the frequency domain.
  arXiv  Detail & Related papers  (2024-02-04T08:23:41Z)
• OrionBench: Benchmarking Time Series Generative Models in the Service of the End-User [8.05635934199494]
  OrionBench is a continuous benchmarking framework for unsupervised time series anomaly detection models. We show how to use OrionBench, and the performance of pipelines across 17 releases published over the course of four years.
  arXiv  Detail & Related papers  (2023-10-26T19:43:16Z)
• Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting [54.04430089029033]
  We present Lag-Llama, a general-purpose foundation model for time series forecasting based on a decoder-only transformer architecture. Lag-Llama is pretrained on a large corpus of diverse time series data from several domains, and demonstrates strong zero-shot generalization capabilities. When fine-tuned on relatively small fractions of such previously unseen datasets, Lag-Llama achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-10-12T12:29:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.