# Constructing sensible baselines for Integrated Gradients

arXiv: https://arxiv.org/abs/2412.13864 · HTML: https://mlsanity.com/paper/2412.13864/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 9 references that are in the map.
- First posted on arXiv 18 Dec 2024.

## Builds on (most cited first, 2 of 2)

- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy](https://mlsanity.com/paper/2211.03796/) (2022)

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

- [AmpLyze: A Deep Learning Model for Predicting the Hemolytic Concentration](https://mlsanity.com/paper/2507.08162/) (2025)
- [FRInGe: Distribution-Space Integrated Gradients with Fisher--Rao Geometry](https://mlsanity.com/paper/2605.06404/) (2026)

## Abstract (arXiv)

Machine learning methods have seen a meteoric rise in their applications in the scientific community. However, little effort has been put into understanding these "black box" models. We show how one can apply integrated gradients (IGs) to understand these models by designing different baselines, by taking an example case study in particle physics. We find that the zero-vector baseline does not provide good feature attributions and that an averaged baseline sampled from the background events provides consistently more reasonable attributions.