A Survey on Current Practices for Time Series Foundation Model Evaluation

Time series forecasting is present across several domains, such as finance, healthcare, energy, and operations, and foundation models promise to replace the traditional one-model-per-series workflow with a single zero-shot pretrained forecaster applied to these domains. Whether they deliver, and where they stop working, remains unknown. Following a survey (conducted on 1 June 2026 from Scopus) reported in line with the PRISMA guidelines, this study surveys 45 articles across five survey questions, covering what time series foundation models are and how they are designed and trained, how well they perform, what is known about their theoretical learnability limits, what phase diagrams and scaling laws reveal about them, and how controlled synthetic temporal environments are constructed and used to evaluate these models. A taxonomy of how models are built and how they are evaluated shows that the literature concentrates on building and benchmarking time series foundation models. Causal analysis of time series foundation models' abilities and limitations remains underexplored. We conclude that there is significant opportunity for future research in broadening the evaluation methods applied to time series foundation models.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-16
DOI
https://doi.org/10.5281/zenodo.24279624
Primary Topic
Time Series Analysis and Forecasting
Type
preprint

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

A Survey on Current Practices for Time Series Foundation Model Evaluation

Marcos Machado, Faizan Ahmed, Mathis Jander, Ties Dilling
2 links
Zenodo (CERN European Organization for Nuclear Research)
Time Series Analysis and Forecasting
preprint

A Survey on Current Practices for Time Series Foundation Model Evaluation

Marcos Machado, Faizan Ahmed, Mathis Jander, Ties Dilling
preprint en

Abstract

Time series forecasting is present across several domains, such as finance, healthcare, energy, and operations, and foundation models promise to replace the traditional one-model-per-series workflow with a single zero-shot pretrained forecaster applied to these domains. Whether they deliver, and where they stop working, remains unknown. Following a survey (conducted on 1 June 2026 from Scopus) reported in line with the PRISMA guidelines, this study surveys 45 articles across five survey questions, covering what time series foundation models are and how they are designed and trained, how well they perform, what is known about their theoretical learnability limits, what phase diagrams and scaling laws reveal about them, and how controlled synthetic temporal environments are constructed and used to evaluate these models. A taxonomy of how models are built and how they are evaluated shows that the literature concentrates on building and benchmarking time series foundation models. Causal analysis of time series foundation models' abilities and limitations remains underexplored. We conclude that there is significant opportunity for future research in broadening the evaluation methods applied to time series foundation models.

Zenodo (CERN European Organization for Nuclear Research)
Saxion (NL), University of Twente (NL)
European Commission
Time Series Analysis and Forecasting
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon