# si4onnx: A Python package for Selective Inference in Deep Learning Models

arXiv: https://arxiv.org/abs/2501.17415 · HTML: https://mlsanity.com/paper/2501.17415/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jan 2025.

## Built on by (most cited first, 5 of 5)

- [Quantifying Statistical Significance of Deep Nearest Neighbor Anomaly Detection via Selective Inference](https://mlsanity.com/paper/2502.12978/) (2025)
- [Statistical Inference for Autoencoder-based Anomaly Detection after Representation Learning-based Domain Adaptation](https://mlsanity.com/paper/2508.07049/) (2025)
- [Statistical Test for Saliency Maps of Graph Neural Networks via Selective Inference](https://mlsanity.com/paper/2505.16893/) (2025)
- [Selective Inference for Deep Clustering in Latent Spaces](https://mlsanity.com/paper/2609.28756/) (2026)
- [Statistical Testing for Multiple Instance Learning via Selective Inference with Applications to Computational Pathology](https://mlsanity.com/paper/2609.31712/) (2026)

## Abstract (arXiv)

In this paper, we introduce si4onnx, a package for performing selective inference on deep learning models. Techniques such as CAM in XAI and reconstruction-based anomaly detection using VAE can be interpreted as methods for identifying significant regions within input images. However, the identified regions may not always carry meaningful significance. Therefore, evaluating the statistical significance of these regions represents a crucial challenge in establishing the reliability of AI systems. si4onnx is a Python package that enables straightforward implementation of hypothesis testing with controlled type I error rates through selective inference. It is compatible with deep learning models constructed using common frameworks such as PyTorch and TensorFlow.