Progress Toward a Muon Neutrino Disappearance Measurement at the SBN Program using SPINE Machine Learning Reconstruction

The Short-Baseline Neutrino (SBN) Program is a neutrino experiment located in the Booster Neutrino Beamline (BNB) at Fermilab. It consists of two liquid argon time projection chamber (LArTPC) detectors: SBND (near detector) and ICARUS (far detector), located respectively 110 and 600 meters downstream from the BNB target. The SBN Program is designed to perform precision neutrino oscillation measurements with a primary focus on searches for electron neutrino appearance and muon neutrino disappearance and directly probing sterile neutrino interpretations of short-baseline anomalies. A key requirement of this program is robust event reconstruction including accurate particle identification (PID) and kinematic reconstruction across a wide range of topologies. To achieve the required precision, we employ the SPINE ("Scalable Particle Imaging with Neural Embeddings") package, a state-of-the-art machine learning reconstruction framework. This work focuses on the muon neutrino disappearance analysis at the SBN Program, including optimization of muon neutrino event selection, background removal, and control of detector systematics. This talk will discuss the current status of this analysis and highlight the impact of SPINE on improving reconstruction and systematic robustness at the SBN Program.