# Unsupervised Symbolic Anomaly Detection

arXiv: https://arxiv.org/abs/2603.17575 · HTML: https://mlsanity.com/paper/2603.17575/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 32 references that are in the map.
- First posted on arXiv 18 Mar 2026.

## Builds on (most cited first, 12 of 12)

- [A Unifying Review of Deep and Shallow Anomaly Detection](https://mlsanity.com/paper/2009.11732/) (2020)
- [ADBench: Anomaly Detection Benchmark](https://mlsanity.com/paper/2206.09426/) (2022)
- [Deep Learning for Medical Anomaly Detection -- A Survey](https://mlsanity.com/paper/2012.02364/) (2020)
- [Interpretable Scientific Discovery with Symbolic Regression: A Review](https://mlsanity.com/paper/2211.10873/) (2022)
- [Online-compatible Unsupervised Non-resonant Anomaly Detection](https://mlsanity.com/paper/2111.06417/) (2021)
- [Meta-survey on outlier and anomaly detection](https://mlsanity.com/paper/2312.07101/) (2023)
- [Explainable Fraud Detection with Deep Symbolic Classification](https://mlsanity.com/paper/2312.00586/) (2023)
- [A Comparison of Recent Algorithms for Symbolic Regression to Genetic Programming](https://mlsanity.com/paper/2406.03585/) (2024)
- [Research and application of Transformer based anomaly detection model: A literature review](https://mlsanity.com/paper/2402.08975/) (2024)
- [Unsupervised Surrogate Anomaly Detection](https://mlsanity.com/paper/2504.20733/) (2025)
- [Outlier Detection Bias Busted: Understanding Sources of Algorithmic Bias through Data-centric Factors](https://mlsanity.com/paper/2408.13667/) (2024)
- [Towards Evolutionary Optimization Using the Ising Model](https://mlsanity.com/paper/2511.15377/) (2025)

## Built on by (most cited first, 1 of 1)

- [Witnesses Explain Anomalies](https://mlsanity.com/paper/2609.03826/) (2026)

## Abstract (arXiv)

We propose SYRAN, an unsupervised anomaly detection method based on symbolic regression. Instead of encoding normal patterns in an opaque, high-dimensional model, our method learns an ensemble of human-readable equations that describe symbolic invariants: functions that are approximately constant on normal data. Deviations from these invariants yield anomaly scores, so that the detection logic is interpretable by construction, rather than via post-hoc explanation. Experimental results demonstrate that SYRAN is highly interpretable, providing equations that correspond to known scientific or medical relationships, and maintains strong anomaly detection performance comparable to that of state-of-the-art methods.