The proton looks like a solid ball, but inside it's a hive of activity: quarks exchange gluons — the particles that bind them together. Gluons pop in and out of existence, and their distribution within the proton is not just a curious detail but a key to predictions at the Large Hadron Collider. Previously, these distributions (known as parton distribution functions) were extracted from data like fish from water: the catch was sorted into bins, and each bin was counted. But this sorting loses fine details.
Now physicists have tried a different approach: feed the entire catch to a neural network without any bins. The network learns from millions of collision events where pairs of top quarks, the heaviest known particles, are produced. It looks at raw, unbinned data from the detector and teases out patterns on its own. This is the first time such an approach has been applied to the gluon distribution, and the precision has improved noticeably.
This method doesn't just improve the numbers. It removes the reliance on crude assumptions about how errors are correlated. When data isn't chopped into pieces, the neural network sees the full picture and makes fewer mistakes. For the future High-Luminosity LHC, where data will be many times more abundant, such precision will become a necessity.
as written by the authors arXiv:2604.13157
The precise determination of the parton distribution functions (PDFs) of the proton is an essential ingredient for LHC analyses, including for those at the upcoming High-Luminosity LHC. So far, PDFs are determined from global fits to binned low-dimensional data obtained from unfolded hard-scattering cross section measurements. In this work we demonstrate for the first time the feasibility of neural simulation-based inference (NSBI) for constraining the proton PDFs using a high-dimensional unbinned data set. Exploiting the full statistical power of unbinned data removes the loss of information inherited by the binning procedure. As a proof-of-concept, we determine the gluon PDF from simulated data of top quark pair production at the LHC with $$\sqrt{s}=13$$ TeV. Taking into account both experimental and theoretical systematic uncertainties in the detector-level features, we demonstrate how the NSBI pipeline achieves significant improvements in precision compared to existing low-dimensional binned analyses. Our results illustrate the potential of unbinned inference to reduce the reliance on coarse approximations of uncertainties and their correlations entering PDF determinations, hence contributing to a new paradigm of unbinned detector-level ML-assisted measurements at the LHC.
Gluons were discovered in 1979 in an experiment at the PETRA accelerator in Hamburg: three jets of particles from an electron-positron collision revealed the presence of a third, invisible particle.
In the series 'Star Trek', quarks and gluons are mentioned as the energy source for the warp drive, although in reality their internal dynamics still baffle physicists.