TSFMAudit detects pretraining contamination in time series foundation models via probe adaptation dynamics (faster loss drop, smaller backbone shift), tested on 6 models and 187 datasets against 10 LLM-derived baselines.
hub Mixed citations
Gift-eval: A benchmark for general time series forecasting model evaluation
Mixed citation behavior. Most common role is background (50%).
40
Pith papers citing it
Background
50% of classified citations
abstract
Time series foundation models excel in zero-shot forecasting, handling diverse tasks without explicit training. However, the advancement of these models has been hindered by the lack of comprehensive benchmarks. To address this gap, we introduce the General Time Series Forecasting Model Evaluation, GIFT-Eval, a pioneering benchmark aimed at promoting evaluation across diverse datasets. GIFT-Eval encompasses 23 datasets over 144,000 time series and 177 million data points, spanning seven domains, 10 frequencies, multivariate inputs, and prediction lengths ranging from short to long-term forecasts. To facilitate the effective pretraining and evaluation of foundation models, we also provide a non-leaking pretraining dataset containing approximately 230 billion data points. Additionally, we provide a comprehensive analysis of 17 baselines, which includes statistical models, deep learning models, and foundation models. We discuss each model in the context of various benchmark characteristics and offer a qualitative analysis that spans both deep learning and foundation models. We believe the insights from this analysis, along with access to this new standard zero-shot time series forecasting benchmark, will guide future developments in time series foundation models. Code, data, and the leaderboard can be found at https://github.com/SalesforceAIResearch/gift-eval .
hub tools
citation-role summary
background 3
baseline 2
extension 1
citation-polarity summary
representative citing papers
TabArena launches a dynamic, updatable benchmarking system for tabular ML that shows boosted trees remain competitive, deep learning matches them under larger budgets with ensembling, foundation models excel on small data, and cross-model ensembles advance SOTA while flagging validation overfitting.
Tabular foundation models excel on tiny- to medium-sized IID data but are outperformed by traditional tree-based and deep learning models on non-IID, large, and high-dimensional datasets, based on evaluations across 11 models and 142 datasets in the new BeyondArena benchmark.
CloudCons benchmark shows foundation models' superior zero-shot forecasting does not automatically yield better resource consolidation decisions, with predictive quantile choice acting as a key lever for efficiency-reliability trade-offs.
Long input windows are required to identify the generative process in time series forecasting even for short-memory processes, and decoupling identification from forecasting improves scalability.
Olivia harmonizes time series datasets via normalized power spectral density using a Harmonizer module and resonator-based HarmonicAttention, achieving state-of-the-art zero-shot, few-shot, and full-shot forecasting on TSLib, GIFT-Eval, and GluonTS benchmarks.
ISOMORPH supplies the first public configurable digital-twin simulator for multi-echelon logistics networks together with generated datasets and zero-shot foundation-model benchmarks that exceed GIFT-Eval MASE at short horizons.
Time series foundation models match the performance of specialized models for day-ahead load forecasting while providing explanations that match domain knowledge on weather and calendar effects.
TempusBench is a new evaluation framework for time-series forecasting models that supplies fresh non-overlapping datasets, tasks beyond horizon and domain, consistent tuning across models, and visualization tools.
TS-Arena is a live pre-registration platform that evaluates time series forecasts on future data streams to eliminate information leakage.
Super-Linear introduces a pretrained MoE architecture using frequency-specialized linear experts and spectral gating for efficient general time series forecasting.
A curated 142-billion-point real-world multivariate time series corpus improves zero-shot forecasting when combined with existing synthetic and univariate pretraining data across four foundation models.
Zero-shot time series foundation models largely fail to beat econometric benchmarks for realized volatility forecasting, with only TTM achieving a narrow, calibration-driven edge.
Aionoscope shows that time-series representations recover coarse signal types reliably but expose dense latent states like phase and amplitude much less reliably, with best dense-probe R² at 0.689 versus oracle 0.999.
Presents a fail-closed certification protocol for determining when forecasting leaderboard winners are deployment-actionable, using a traffic dataset to show friction-induced reversals and an audit to prevent overclaiming.
Timeflies reformulates time series forecasting as joint inference of future observability and value estimation using coupled observation and value streams.
TimeRouter routes among time-series foundation models via discriminative routing, selective gating and ensemble fallback, reporting SOTA LB MASE 0.6765 on GIFT-EVAL.
Equal-weight mixture of synthetic generators matches or exceeds best single generator for time series foundation model pretraining and strengthens further with real data.
GITCO delivers +1.95% average MASE reduction on TimesFM 2.5 across 53 datasets by gated inference-time suppression of anomalous patches, capturing 89.9% of the improvement upper bound.
UniTok tokenizes time series for an off-the-shelf LLM foundation model that unifies forecasting, generation, and classification through next-token prediction and training-free inference.
AME-TS is a structure-guided sparse MoE foundation model for time series that aligns expert routing with series-level temporal descriptors to achieve strong accuracy-efficiency tradeoffs on GIFT-Eval while improving specialization stability.
RareCP improves interval efficiency for time series conformal prediction by retrieving and weighting regime-specific calibration examples while adapting to drift and maintaining coverage.
Foundation models outperform dataset-specific machine learning in energy time series forecasting across 54 datasets in 9 categories.
IDOBE compiles over 10,000 epidemiological outbreaks into a public benchmark and shows that MLP-based models deliver the most robust short-term forecasts while statistical methods hold a slight edge pre-peak.
citing papers explorer
-
TabArena: A Living Benchmark for Machine Learning on Tabular Data
TabArena launches a dynamic, updatable benchmarking system for tabular ML that shows boosted trees remain competitive, deep learning matches them under larger budgets with ensembling, foundation models excel on small data, and cross-model ensembles advance SOTA while flagging validation overfitting.
-
FETS Benchmark: Foundation Models Outperform Dataset-specific Machine Learning in Energy Time Series Forecasting
Foundation models outperform dataset-specific machine learning in energy time series forecasting across 54 datasets in 9 categories.
-
TimeRFT: Stimulating Generalizable Time Series Forecasting for TSFMs via Reinforcement Finetuning
TimeRFT applies reinforcement learning with multi-faceted step-wise rewards and informative sample selection to improve generalization and accuracy in TSFM adaptation beyond supervised fine-tuning.