Harnessing data-driven methods for precise model independent event shape estimation in relativistic heavy-ion collisions

This study demonstrates the application of supervised machine learning (ML) techniques to distinguish between isotropic and jet-like event topologies in heavy-ion collisions via the spherocity observable. State-of-the-art ML algorithms, optimized through systematic hyperparameter tuning, are employed to predict both traditional transverse spherocity $S_0$ and unweighted transverse spherocity $S_0^{p_{\mathrm{T}}=1}$ directly from raw event data. Moreover, the results from this study demonstrated that our approach remains largely model-independent, underscoring its potential applicability in future experimental heavy-ion physics analyses.