# Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy

arXiv: https://arxiv.org/abs/2509.21190 · HTML: https://mlsanity.com/paper/2509.21190/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Model collapse from synthetic data, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 29 of its 46 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Placed in

- Synthetic data and self-improvement for LLMs / [Model collapse from synthetic data](https://mlsanity.com/synth/model-collapse-from-synthetic-data/)

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [MOMENT: A Family of Open Time-series Foundation Models](https://mlsanity.com/paper/2402.03885/) (2024)
- [Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy](https://mlsanity.com/paper/2110.02642/) (2021)
- [Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts](https://mlsanity.com/paper/2409.16040/) (2024)
- [TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data](https://mlsanity.com/paper/2201.07284/) (2022)
- [A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data](https://mlsanity.com/paper/1811.08055/) (2018)
- [Sundial: A Family of Highly Capable Time Series Foundation Models](https://mlsanity.com/paper/2502.00816/) (2025)
- [Time-Series Anomaly Detection Service at Microsoft](https://mlsanity.com/paper/1906.03821/) (2019)
- [Deep Learning for Time Series Anomaly Detection: A Survey](https://mlsanity.com/paper/2211.05244/) (2022)
- [ForecastPFN: Synthetically-Trained Zero-Shot Forecasting](https://mlsanity.com/paper/2311.01933/) (2023)
- [DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection](https://mlsanity.com/paper/2306.10347/) (2023)
- [ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoning](https://mlsanity.com/paper/2412.03104/) (2024)
- [UniTS: A Unified Multi-Task Time Series Model](https://mlsanity.com/paper/2403.00131/) (2024)
- [CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patching](https://mlsanity.com/paper/2410.12261/) (2024)
- [Local Evaluation of Time Series Anomaly Detection Algorithms](https://mlsanity.com/paper/2206.13167/) (2022)
- [TimeSeriesExam: A time series understanding exam](https://mlsanity.com/paper/2410.14752/) (2024)
- [Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoders](https://mlsanity.com/paper/2405.15273/) (2024)
- [TimePFN: Effective Multivariate Time Series Forecasting with Synthetic Data](https://mlsanity.com/paper/2502.16294/) (2025)
- [CALDA: Improving Multi-Source Time Series Domain Adaptation with Contrastive Adversarial Learning](https://mlsanity.com/paper/2109.14778/) (2021)
- [Position: Quo Vadis, Unsupervised Time Series Anomaly Detection?](https://mlsanity.com/paper/2405.02678/) (2024)
- [Mamba4Cast: Efficient Zero-Shot Time Series Forecasting with State Space Models](https://mlsanity.com/paper/2410.09385/) (2024)
- [AER: Auto-Encoder with Regression for Time Series Anomaly Detection](https://mlsanity.com/paper/2212.13558/) (2022)
- [DACAD: Domain Adaptation Contrastive Learning for Anomaly Detection in Multivariate Time Series](https://mlsanity.com/paper/2404.11269/) (2024)
- [Patch-based Memory Gate Model in Time Series Foundation Model](https://mlsanity.com/paper/2509.18751/) (2025)
- [CICADA: Cross-Domain Interpretable Coding for Anomaly Detection and Adaptation in Multivariate Time Series](https://mlsanity.com/paper/2505.00415/) (2025)

## Built on by (most cited first, 10 of 10)

- [From Zero to Hero: Advancing Zero-Shot Foundation Models for Tabular Outlier Detection](https://mlsanity.com/paper/2602.03018/) (2026)
- [AXIS: Explainable Time Series Anomaly Detection with Large Language Models](https://mlsanity.com/paper/2509.24378/) (2025)
- [OATS: Online Data Augmentation for Time Series Foundation Models](https://mlsanity.com/paper/2601.19040/) (2026)
- [Tabby: An Open Pretraining Recipe for Time Series Foundation Models](https://mlsanity.com/paper/2609.13956/) (2026)
- [VETime: Vision Enhanced Zero-Shot Time Series Anomaly Detection](https://mlsanity.com/paper/2602.16681/) (2026)
- [LLM-Generated Feature Pools for Time Series Anomaly Detection](https://mlsanity.com/paper/2609.21801/) (2026)
- [Beyond Empirical Support: Structured Outlier Generation via Sinkhorn Optimal Transport](https://mlsanity.com/paper/2609.31470/) (2026)
- [Supervision Recovery for Time Series Anomaly Detection via Context-Anchored Pairing](https://mlsanity.com/paper/2609.33610/) (2026)
- [Generalist Representation, Specialist Detection: TS-Router for Time-Series Anomaly Detection](https://mlsanity.com/paper/2610.00978/) (2026)
- [Anlu: Enabling In-Context Time Series Anomaly Detection in Foundation Models via Counterfactual Supervision](https://mlsanity.com/paper/2610.06180/) (2026)

## Abstract (arXiv)

Time series anomaly detection (TSAD) is a critical task, but developing models that generalize to unseen data in a zero-shot manner remains challenging. Existing foundation models for TSAD often rely on reconstruction-error scoring at inference time, which can miss subtle anomalies that are well reconstructed and can falsely flag complex but normal patterns in unseen domains. We introduce TimeRCD, a foundation model for TSAD built on Relative Context Discrepancy (RCD), a pre-training paradigm that trains the model to detect anomalies by comparing a query pattern with its surrounding context. This relational formulation, implemented with a standard Transformer architecture, enables the model to infer normality from the input context rather than relying on fixed global normal patterns. We further construct a large-scale synthetic corpus with context-dependent anomaly labels to provide supervised pre-training signals for RCD. Experiments across diverse benchmarks show that TimeRCD outperforms existing general-purpose and anomaly-specific foundation models in most zero-shot TSAD settings, while remaining competitive with dataset-specific full-shot baselines. These results provide empirical evidence that RCD is an effective direction for building robust and generalizable TSAD models.