Search papers, labs, and topics across Lattice.
This study introduces a conditional diffusion model that directly maps raw semi-inclusive deep inelastic scattering (SIDIS) event kinematics to transverse momentum dependent parton distribution functions (TMD PDFs), circumventing the limitations of traditional parameterized fitting methods. The model demonstrates its effectiveness by accurately recovering underlying TMD distributions from simulated SIDIS data at CLAS12 kinematics, showing that it can produce reliable estimates even with as few as 1,000 conditioning events. This approach not only enhances flexibility in distribution extraction but also provides informative uncertainty quantification that improves with increased event statistics, making it highly relevant for current and future experiments.
A conditional diffusion model can accurately extract TMD PDFs from raw SIDIS data, even in statistics-limited scenarios, revolutionizing how we approach parton distribution functions.
Extracting transverse momentum dependent parton distribution functions (TMD PDFs) from semi-inclusive deep inelastic scattering (SIDIS) data is a central goal of the nucleon structure program at Jefferson Lab and the future Electron-Ion Collider. Traditional extraction methods rely on parameterized functional forms and iterative fitting, which can limit the flexibility of the resulting distributions and make uncertainty quantification cumbersome. We present a conditional diffusion model that learns to map raw SIDIS event kinematics directly to TMD PDFs, bypassing explicit functional assumptions. Evaluated on simulated SIDIS data at CLAS12 kinematics, the model recovers the underlying TMD with informative uncertainties that narrow steadily with increasing event statistics, and produces reliable estimates even with as few as 1,000 conditioning events, a statistics-limited regime directly relevant to ongoing and planned experiments.
