{"ID":2892669,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.15084","arxiv_id":"2507.15084","title":"Simulation-Prior Independent Neural Unfolding Procedure","abstract":"Machine learning allows unfolding high-dimensional spaces without binning at the LHC. The new SPINUP method extracts the unfolded distribution based on a neural network encoding the forward mapping, making it independent of the prior from the simulated training data. It is made efficient through neural importance sampling, and ensembling can be used to estimate the effect of information loss in the forward process. We showcase SPINUP for unfolding detector effects on jet substructure observables and for unfolding to parton level of associated Higgs and single-top production.","short_abstract":"Machine learning allows unfolding high-dimensional spaces without binning at the LHC. The new SPINUP method extracts the unfolded distribution based on a neural network encoding the forward mapping, making it independent of the prior from the simulated training data. It is made efficient through neural importance sampl...","url_abs":"https://arxiv.org/abs/2507.15084","url_pdf":"https://arxiv.org/pdf/2507.15084v1","authors":"[\"Anja Butter\",\"Theo Heimel\",\"Nathan Huetsch\",\"Michael Kagan\",\"Tilman Plehn\"]","published":"2025-07-20T18:43:03Z","proceeding":"hep-ph","tasks":"[\"hep-ph\",\"cs.LG\",\"hep-ex\"]","methods":"[]","has_code":false}