# A practical guide to unbinned unfolding

## TL;DR

This paper provides a guide on using machine learning for unbinned unfolding in particle physics to improve data analysis.

## Contribution

The paper offers practical recommendations for implementing unbinned unfolding techniques in real-world particle physics experiments.

## Key findings

- Unbinned unfolding allows for higher-dimensional analyses compared to traditional binned methods.
- Machine learning techniques enable more flexible and accurate data unfolding in particle physics.
- Researchers have successfully applied these methods to real experimental data.

## Abstract

Unfolding, in the context of high-energy particle physics, refers to the process of removing detector distortions in experimental data. The resulting unfolded measurements are straightforward to use for direct comparisons between experiments and a wide variety of theoretical predictions. For decades, popular unfolding strategies were designed to operate on data formatted as one or more binned histograms. In recent years, new strategies have emerged that use machine learning to unfold datasets in an unbinned manner, allowing for higher-dimensional analyses and more flexibility for current and future users of the unfolded data. This guide comprises recommendations and practical considerations from researchers across a number of major particle physics experiments who have recently put these techniques into practice on real data.