# FoMo X: Modular Explainability Signals for Outlier Detection Foundation Models

arXiv: https://arxiv.org/abs/2603.17570 · HTML: https://mlsanity.com/paper/2603.17570/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 62 references that are in the map.
- First posted on arXiv 18 Mar 2026.

## Builds on (most cited first, 30 of 33)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022)
- [DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection](https://mlsanity.com/paper/2108.07610/) (2021)
- [A Unifying Review of Deep and Shallow Anomaly Detection](https://mlsanity.com/paper/2009.11732/) (2020)
- [Transformers Can Do Bayesian Inference](https://mlsanity.com/paper/2112.10510/) (2021)
- [ADBench: Anomaly Detection Benchmark](https://mlsanity.com/paper/2206.09426/) (2022)
- [TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models](https://mlsanity.com/paper/2511.08667/) (2025)
- [On Diffusion Modeling for Anomaly Detection](https://mlsanity.com/paper/2305.18593/) (2023)
- [Real-TabPFN: Improving Tabular Foundation Models via Continued Pre-training With Real-World Data](https://mlsanity.com/paper/2507.03971/) (2025)
- [A Survey on Explainable Anomaly Detection](https://mlsanity.com/paper/2210.06959/) (2022)
- [TabPFN Unleashed: A Scalable and Effective Solution to Tabular Classification Problems](https://mlsanity.com/paper/2502.02527/) (2025)
- [On the Nature and Types of Anomalies: A Review of Deviations in Data](https://mlsanity.com/paper/2007.15634/) (2020)
- [Unsupervised anomaly detection algorithms on real-world data: how many do we need?](https://mlsanity.com/paper/2305.00735/) (2023)
- [Robust and Explainable Autoencoders for Unsupervised Time Series Outlier Detection---Extended Version](https://mlsanity.com/paper/2204.03341/) (2022)
- [Comparing the Pearson and Spearman Correlation Coefficients Across Distributions and Sample Sizes: A Tutorial Using Simulations and Empirical Data](https://mlsanity.com/paper/2408.15979/) (2024)
- [Online-compatible Unsupervised Non-resonant Anomaly Detection](https://mlsanity.com/paper/2111.06417/) (2021)
- [TabPFN: One Model to Rule Them All?](https://mlsanity.com/paper/2505.20003/) (2025)
- [Meta-survey on outlier and anomaly detection](https://mlsanity.com/paper/2312.07101/) (2023)
- [FoMo-0D: A Foundation Model for Zero-shot Tabular Outlier Detection](https://mlsanity.com/paper/2409.05672/) (2024)
- [Dropout Distillation for Efficiently Estimating Model Confidence](https://mlsanity.com/paper/1809.10562/) (2018)
- [From Zero to Hero: Advancing Zero-Shot Foundation Models for Tabular Outlier Detection](https://mlsanity.com/paper/2602.03018/) (2026)
- [Unveiling the Unseen: A Comprehensive Survey on Explainable Anomaly Detection in Images and Videos](https://mlsanity.com/paper/2302.06670/) (2023)
- [Why Are You Weird? Infusing Interpretability in Isolation Forest for Anomaly Detection](https://mlsanity.com/paper/2112.06858/) (2021)
- [What exactly has TabPFN learned to do?](https://mlsanity.com/paper/2502.08978/) (2025)
- [Periodicity Detection of Outlier Sequences Using Constraint Based Pattern Tree with MAD](https://mlsanity.com/paper/1507.01685/) (2015)
- [Prototypes as Explanation for Time Series Anomaly Detection](https://mlsanity.com/paper/2307.01601/) (2023)
- [We Need to Rethink Benchmarking in Anomaly Detection](https://mlsanity.com/paper/2507.15584/) (2025)
- [Unsupervised Surrogate Anomaly Detection](https://mlsanity.com/paper/2504.20733/) (2025)

## Built on by (most cited first, 2 of 2)

- [CORE: In-Context Reconstruction for Unified Tabular Anomaly Detection](https://mlsanity.com/paper/2607.27615/) (2026)
- [Why Ranking Anomaly Detection Algorithms Isn't as Reliable as You May Think](https://mlsanity.com/paper/2608.04613/) (2026)

## Abstract (arXiv)

Tabular foundation models, specifically Prior-Data Fitted Networks (PFNs), have revolutionized outlier detection (OD) by enabling unsupervised zero-shot adaptation to new datasets without training. However, despite their predictive power, these models typically function as opaque black boxes, outputting scalar outlier scores that lack the operational context required for safety-critical decision-making. Existing post-hoc explanation methods are often computationally prohibitive for real-time deployment or fail to capture the epistemic uncertainty inherent in zero-shot inference. In this work, we introduce FoMo-X, a modular framework that equips OD foundation models with intrinsic, lightweight diagnostic capabilities. We leverage the insight that the frozen embeddings of a pretrained PFN backbone already encode rich, context-conditioned relational information. FoMo-X attaches auxiliary diagnostic heads to these embeddings, trained offline using the same generative simulator prior as the backbone. This allows us to distill computationally expensive properties, such as Monte Carlo dropout based epistemic uncertainty, into a deterministic, single-pass inference. We instantiate FoMo-X with two novel heads: a Severity Head that discretizes deviations into interpretable risk tiers, and an Uncertainty Head that provides calibrated confidence measures. Extensive evaluation on synthetic and real-world benchmarks (ADBench) demonstrates that FoMo-X recovers ground-truth diagnostic signals with high fidelity and negligible inference overhead. By bridging the gap between foundation model performance and operational explainability, FoMo-X offers a scalable path toward trustworthy, zero-shot outlier detection.