2026-05-27原文

TSFMAudit: Data Contamination Auditing in Forecasting Time Series Foundation Models

First work to study pretraining contamination auditing for time series foundation models (TSFMs). Proposes TSFMAudit, a method based on probe adaptation dynamics, detecting contamination via faster loss reduction and smaller backbone movement after fine-tuning probes. Evaluated on 6 TSFMs and 187 datasets, outperforming 10 baselines adapted from LLM literature.

Article intelligence

InvestorsAdvanced

Key points

First formulation of pretraining contamination auditing for TSFMs.
TSFMAudit leverages probe adaptation dynamics to detect anomalous adaptation efficiency.
Validated on 6 models and 187 datasets, surpassing LLM-adapted baselines.

Why it matters

This matters because first formulation of pretraining contamination auditing for TSFMs.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

[2605.26161] TSFMAudit: Data Contamination Auditing in Forecasting Time Series Foundation Models

[Submitted on 24 May 2026]

Title:TSFMAudit: Data Contamination Auditing in Forecasting Time Series Foundation Models

View a PDF of the paper titled TSFMAudit: Data Contamination Auditing in Forecasting Time Series Foundation Models, by Hongkai Li and 9 other authors

View PDF HTML (experimental)

Abstract:Time series foundation models (TSFMs) are increasingly pretrained on large corpora, raising concerns that evaluation datasets may have been exposed during pretraining and thus yield overly optimistic performance estimates. Auditing such contamination is challenging in time series because signals are continuous and heterogeneous, and often lack corpus documentation. To the best of our knowledge, this is the first work to study pretraining contamination auditing for TSFMs. We formalize the problem of pretraining contamination auditing for TSFMs and propose TSFMAudit, a method based on probe adaptation dynamics. Our key intuition is that contamination manifests as unusually efficient adaptation: after a fine tuning probe, contaminated datasets tend to exhibit faster loss reduction with smaller backbone movement. We evaluate TSFMAudit on 6 TSFMs and 187 datasets using documented training source evidence as supervision, and compare against 10 competitive baselines adapted from the LLM literature.

Comments: 22 pages, 7 figures, 9 tables

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

Cite as: arXiv:2605.26161 [cs.LG]

(or arXiv:2605.26161v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2605.26161

arXiv-issued DOI via DataCite

Submission history

From: Hongkai Li [view email] [v1] Sun, 24 May 2026 14:59:12 UTC (220 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled TSFMAudit: Data Contamination Auditing in Forecasting Time Series Foundation Models, by Hongkai Li and 9 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-05

Change to browse by:

cs cs.AI

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)