Beyond bins: A Machine-learned SMEFT analysis of top quarks

The top quark, the heaviest known fundamental particle, plays a crucial role in shaping our understanding of the universe. It interacts strongly with the Higgs boson and could be a key to new physics beyond the Standard Model. However, extracting precise information from top quark interactions at the Large Hadron Collider (LHC) remains a major challenge due to the complexity of its production and decay. This research project aims to overcome these limitations by leveraging cutting-edge machine learning (ML) techniques to analyze top quark events with unprecedented precision. Traditionally, particle physics experiments summarize collision data using simplified representations, discarding much of the intricate event structure. This project revolutionizes the approach by fully utilizing high-dimensional event data. Advanced ML algorithms will be trained to recognize patterns in the collisions that would otherwise be missed, allowing us to extract the most precise possible constraints on the top quark`s interactions. This could provide a window into new physics at energy scales far beyond direct experimental reach. A key focus of the research is on the Standard Model Effective Field Theory (SMEFT), a powerful framework that describes potential deviations from known physics in a systematic way. Using ML-driven techniques, we will perform an unbinned analysis of top quark pair production, significantly improving sensitivity to new physics effects compared to traditional methods. This project will not only enhance our understanding of the top quark but also set new standards for data analysis in high-energy physics. The outcomes will provide crucial input for future global SMEFT studies and offer a novel methodology that can be applied to a wide range of fundamental physics measurements. By combining the power of modern computational techniques with the precision of LHC data, we take an important step toward uncovering new laws of nature.