# TACTIC for Navigating the Unknown: Tabular Anomaly deteCTion via In-Context inference

arXiv: https://arxiv.org/abs/2603.14171 · HTML: https://mlsanity.com/paper/2603.14171/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 36 references that are in the map.
- First posted on arXiv 15 Mar 2026.

## Builds on (most cited first, 19 of 19)

- [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022)
- [GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training](https://mlsanity.com/paper/1805.06725/) (2018)
- [Transformers Can Do Bayesian Inference](https://mlsanity.com/paper/2112.10510/) (2021)
- [TabICL: A Tabular Foundation Model for In-Context Learning on Large Data](https://mlsanity.com/paper/2502.05564/) (2025)
- [ADBench: Anomaly Detection Benchmark](https://mlsanity.com/paper/2206.09426/) (2022)
- [PyOD: A Python Toolbox for Scalable Outlier Detection](https://mlsanity.com/paper/1901.01588/) (2019)
- [ECOD: Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functions](https://mlsanity.com/paper/2201.00382/) (2022)
- [COPOD: Copula-Based Outlier Detection](https://mlsanity.com/paper/2009.09463/) (2020)
- [Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models](https://mlsanity.com/paper/2510.21204/) (2025)
- [On Diffusion Modeling for Anomaly Detection](https://mlsanity.com/paper/2305.18593/) (2023)
- [TabPFGen -- Tabular Data Generation with TabPFN](https://mlsanity.com/paper/2406.05216/) (2024)
- [Benchmarking Unsupervised Outlier Detection with Realistic Synthetic Data](https://mlsanity.com/paper/2004.06947/) (2020)
- [Fine-tuned In-Context Learning Transformers are Excellent Tabular Data Classifiers](https://mlsanity.com/paper/2405.13396/) (2024)
- [TabEBM: A Tabular Data Augmentation Method with Distinct Class-Specific Energy-Based Models](https://mlsanity.com/paper/2409.16118/) (2024)
- [OneFlow: One-class flow for anomaly detection based on a minimal volume region](https://mlsanity.com/paper/2010.03002/) (2020)
- [Scalable, Explainable and Provably Robust Anomaly Detection with One-Step Flow Matching](https://mlsanity.com/paper/2510.18328/) (2025)
- [Adapting k-means algorithms for outliers](https://mlsanity.com/paper/2007.01118/) (2020)
- [ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data](https://mlsanity.com/paper/2505.10704/) (2025)
- [TabClustPFN: A Prior-data Fitted Network for Tabular Data Clustering](https://mlsanity.com/paper/2601.21656/) (2026)

## Built on by (most cited first, 7 of 7)

- [Beyond IID: How General Are Tabular Foundation Models, Really?](https://mlsanity.com/paper/2606.30410/) (2026)
- [FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse Tabular Tasks](https://mlsanity.com/paper/2606.30336/) (2026)
- [In-Context Density Estimation for Tabular Data](https://mlsanity.com/paper/2608.09348/) (2026)
- [When Less Compute Is More: Adaptive Early Exit Improves Pretrained Outlier Detection](https://mlsanity.com/paper/2609.32898/) (2026)
- [TaskBridge: Bridging Unsupervised Tabular Anomaly Detection and In-Context Learning via Virtual Tasks](https://mlsanity.com/paper/2609.36968/) (2026)
- [Adapting prior-data fitted networks for tabular anomaly detection](https://mlsanity.com/paper/2610.06693/) (2026)
- [TICDA: Tabular In-Context Data Attribution](https://mlsanity.com/paper/2610.07996/) (2026)

## Abstract (arXiv)

Anomaly detection for tabular data has been a long-standing unsupervised learning problem that remains a major challenge for current deep learning models. Recently, in-context learning has emerged as a new paradigm that has shifted efforts from task-specific optimization to large-scale pretraining aimed at creating foundation models that generalize across diverse datasets. Although in-context models, such as TabPFN, perform well in supervised problems, their learned classification-based priors may not readily extend to anomaly detection. In this paper, we study in-context models for anomaly detection and show that the unsupervised extensions to TabPFN exhibit unstable behavior, particularly in noisy or contaminated contexts, in addition to the high computational cost. We address these challenges and introduce TACTIC, an in-context anomaly detection approach based on pretraining with anomaly-centric synthetic priors, which provides fast and data-dependent reasoning about anomalies while avoiding dataset-specific tuning. In contrast to typical score-based approaches, which produce uncalibrated anomaly scores that require post-processing (e.g. threshold selection or ranking heuristics), the proposed model is trained as a discriminative predictor, enabling unambiguous anomaly decisions in a single forward pass. Through experiments on real-world datasets, we examine the performance of TACTIC in clean and noisy contexts with varying anomaly rates and different anomaly types, as well as the impact of prior choices on detection quality. Our experiments clearly show that specialized anomaly-centric in-context models such as TACTIC are highly competitive compared to other task-specific methods.