TY  - JOUR
AU  - Gavrikov, Arsenii
AU  - Serafini, Andrea
AU  - Dolzhikov, Dmitry
AU  - Garfagnini, Alberto
AU  - Gonchar, Maxim
AU  - Grassi, Marco
AU  - Andronico, Giuseppe
AU  - Antonelli, Vito
AU  - Barresi, Andrea
AU  - Basilico, Davide
AU  - Beretta, Marco
AU  - Bergnoli, Antonio
AU  - Borghesi, Matteo
AU  - Brigatti, Augusto
AU  - Brugnera, Riccardo
AU  - Bruno, Riccardo
AU  - Budano, Antonio
AU  - Caccianiga, Barbara
AU  - Cammi, Antonio
AU  - Caruso, Rossella
AU  - Cerrone, Vanessa
AU  - Chiesa, Davide
AU  - Clementi, Catia
AU  - Coletta, Claudio
AU  - D’Auria, Lorenzo V.
AU  - Dusini, Stefano
AU  - Fabbri, Andrea
AU  - Farilla, Elia S.
AU  - Felici, Giulietto
AU  - Ferrante, Giovanni
AU  - Giammarchi, Marco G.
AU  - Giudice, Nunzio
AU  - Guardone, Nunzio
AU  - Guizzetti, Rosa Maria
AU  - Houria, Fatima
AU  - Landini, Cecilia
AU  - Lastrucci, Lorenzo
AU  - Lippi, Ivano
AU  - Loi, Lorenzo
AU  - Lombardi, Paolo
AU  - Mantovani, Fabio
AU  - Mari, Stefano M.
AU  - Martini, Agnese
AU  - Miramonti, Lino
AU  - Montuschi, Michele
AU  - Nastasi, Massimiliano
AU  - Orestano, Domizia
AU  - Ortica, Fausto
AU  - Paoloni, Alessandro
AU  - Pelicci, Luca
AU  - Percalli, Elisa
AU  - Petrucci, Fabrizio
AU  - Previtali, Ezio
AU  - Ranucci, Gioacchino
AU  - Re, Alessandra C.
AU  - Ricci, Barbara
AU  - Romani, Aldo
AU  - Sirignano, Chiara
AU  - Sisti, Monica
AU  - Stanco, Luca
AU  - Strati, Virginia
AU  - Torri, Marco D. C.
AU  - Tuvè, Cristina
AU  - Venettacci, Carlo
AU  - Verde, Giuseppe
AU  - Votano, Lucia
AU  - JUNO-Italia Consortium
PY  - 2026
DA  - 2026/01/23
TI  - Simulation-based inference for precision neutrino physics through neural Monte Carlo tuning
JO  - Communications Physics
SP  - 63
VL  - 9
IS  - 1
AB  - Precise modeling of detector energy response is crucial for next-generation neutrino experiments, which present computational challenges due to the lack of analytical likelihoods. We propose a solution using neural likelihood estimation within the simulation-based inference framework. We develop two complementary neural density estimators that model likelihoods of calibration data: conditional normalizing flows and a transformer-based regressor. We adopt JUNO — a large neutrino experiment — as a case study. The energy response of JUNO depends on several parameters, all of which should be tuned, given their non-linear behavior and strong correlations in the calibration data. To this end, we integrate the modeled likelihoods with Bayesian nested sampling for parameter inference, achieving uncertainties limited only by statistics with near-zero systematic biases. The normalizing flows model enables unbinned likelihood analysis, while the transformer provides an efficient binned alternative. By providing both options, our framework offers flexibility to choose the most appropriate method for specific needs. Finally, our approach establishes a template for similar applications across experimental neutrino and broader particle physics.
SN  - 2399-3650
UR  - https://doi.org/10.1038/s42005-026-02499-6
DO  - 10.1038/s42005-026-02499-6
ID  - Gavrikov2026
ER  -