Artificial intelligence methods show great promise in increasing the quality and speed of work with large astronomical datasets, but the high complexity of these methods leads to the extraction of dataset-specific, non-robust features. Therefore, such methods do not generalize well across multiple datasets. We present a universal domain adaptation method, DeepAstroUDA, as an approach to overcome this challenge. This algorithm performs semi-supervised domain adaptation (DA) and can be applied to datasets with different data distributions and class overlaps. Non-overlapping classes can be present in any of the two datasets (the labeled source domain, or the unlabeled target domain), and the method can even be used in the presence of unknown classes. We apply our method to three examples of galaxy morphology classification tasks of different complexities (three-class and ten-class problems), with anomaly detection: (1) datasets created after different numbers of observing years from a single survey (Legacy Survey of Space and Time mock data of one and ten years of observations); (2) data from different surveys (Sloan Digital Sky Survey (SDSS) and DECaLS); and (3) data from observing fields with different depths within one survey (wide field and Stripe 82 deep field of SDSS). For the first time, we demonstrate the successful use of DA between very discrepant observational datasets. DeepAstroUDA is capable of bridging the gap between two astronomical surveys, increasing classification accuracy in both domains (up to 40 % on the unlabeled data), and making model performance consistent across datasets. Furthermore, our method also performs well as an anomaly detection algorithm and successfully clusters unknown class samples even in the unlabeled target dataset.

Faced with unresolved tensions between neutrino interaction measurements at few-GeV neutrino energies, current experiments are forced to accept large systematic uncertainties to cover discrepancies between their data and model predictions. In this paper, the widely used pion production model in GENIE is compared to four MINERvA charged current pion production measurements using NUISANCE. Tunings, ie, adjustments of model parameters, to help match GENIE to MINERvA and older bubble chamber data are presented here. We find that scattering off nuclear targets as measured in MINERvA is not in good agreement with scattering off nucleon (hydrogen or deuterium) targets in the bubble chamber data. An additional ad hoc correction for the low-$Q^2$ region, where collective effects are expected to be large, is also presented. While these tunings and corrections improve the agreement of GENIE with the data, the modeling is imperfect. The development of these tunings within the NUISANCE frameworkallows for straightforward extensions to other neutrino event generators and models, and allows omitting and including new data sets as they become available.

We present double-differential measurements of antineutrino charged-current quasielastic scattering in the MINERvA detector. This study improves on a previous single-differential measurement by using updated reconstruction algorithms and interaction models and provides a complete description of observed muon kinematics in the form of a double-differential cross section with respect to muon transverse and longitudinal momentum. We include in our signal definition zero-meson final states arising from multinucleon interactions and from resonant pion production followed by pion absorption in the primary nucleus. We find that model agreement is considerably improved by a model tuned to MINERvA inclusive neutrino scattering data that incorporates nuclear effects such as weak nuclear screening and two-particle, two-hole enhancements.

Single neutral pion production via muon antineutrino charged-current interactions in plastic scintillator (CH) is studied using the MINERvA detector exposed to the NuMI low-energy, wideband antineutrino beam at Fermilab. Measurement of this process constrains models of neutral pion production in nuclei, which is important because the neutral-current analog is a background for ν-e appearance oscillation experiments. The differential cross sections for π0 momentum and production angle, for events with a single observed π0 and no charged pions, are presented and compared to model predictions. These results comprise the first measurement of the π0 kinematics for this process.

Neutrino induced coherent charged pion production on nuclei, $\overline{ u}_\mu A\to\mu^\pm\pi^\mp A$, is a rare inelastic interaction in which the four-momentum squared transfered to the nucleus is nearly zero, leaving it intact. We identify such events in the scintillator of MINERvA by reconstructing |t| from the final state pion and muon momenta and by removing events with evidence of energetic nuclear recoil or production of other final state particles. We measure the total neutrino and antineutrino cross sections as a function of neutrino energy between 2 and 20 GeV and measure flux integrated differential cross sections as a function of $Q^2$, $E_\pi$ and $\theta_\pi$. The $Q^2$ dependence and equality of the neutrino and anti-neutrino cross-sections at finite $Q^2$ provide a confirmation of Adler's PCAC hypothesis.

Final-state kinematic imbalances are measured in mesonless production of ν_{μ}+A→μ^{-}+p+X in the MINERvA tracker. Initial- and final-state nuclear effects are probed using the direction of the μ^{-}-p transverse momentum imbalance and the initial-state momentum of the struck neutron. Differential cross sections are compared to predictions based on current approaches to medium modeling. These models underpredict the cross section at intermediate intranuclear momentum transfers that generally exceed the Fermi momenta. As neutrino interaction models need to correctly incorporate the effect of the nucleus in order to predict neutrino energy resolution in oscillation experiments, this result points to a region of phase space where additional cross section strength is needed in current models, and demonstrates a new technique that would be suitable for use in fine-grained liquid argon detectors where the effect of the nucleus may be even larger.

The Electron-Ion Collider (EIC), a state-of-the-art facility for studying the strong force, is expected to begin commissioning its first experiments in 2028. This is an opportune time for artificial intelligence (AI) to be included from the start at this facility and in all phases that lead up to the experiments. The second annual workshop organized by the AI4EIC working group, which recently took place, centered on exploring all current and prospective application areas of AI for the EIC. This workshop is not only beneficial for the EIC, but also provides valuable insights for the newly established ePIC collaboration at EIC. This paper summarizes the different activities and R&D projects covered across the sessions of the workshop and provides an overview of the goals, approaches and strategies regarding AI/ML in the EIC community, as well as cutting-edge techniques currently studied in other experiments.