Results for “trustworthy design” — Page 5

DOE OSTI2025

CHEMREASONER: Heuristic Search over a Large Language Model’s Knowledge Space using Quantum-Chemical Feedback

The discovery of new catalysts is essential for the design of new and more efficient chemical processes in order to transition to a sustainable future. We introduce an AI-guided computational screening framework unifying linguistic reasoning with quantum-chemistry based feedback from 3D atomistic representations. Our approach formulates catalyst discovery as an uncertain environment where an agent actively searches for highly effective catalysts via the iterative combination of large language model (LLM)-derived hypotheses and atomistic graph neural network (GNN)-derived feedback. Identified catalysts in intermediate search steps undergo structural evaluation based on spatial orientation, reaction pathways, and stability. Scoring functions based on adsorption energies and barriers steer the exploration in the LLM's knowledge space toward energetically favorable, high-efficiency catalysts. We introduce planning methods that automatically guide the exploration without human input, providing competitive performance against expert-enumerated chemical descriptor-based implementations. By integrating language-guided reasoning with computational chemistry feedback, our work pioneers AI-accelerated, trustworthy catalyst discovery.

artificial intelligence↗

DOE OSTI2026

Using AI to Reproduce Neutrino Cross Section Analysis - Prototyping the Neutrino Discovery Platform

The Neutrino Discovery Platform (NDP) aims to accelerate DUNE-era science by making the neutrino program's existing datasets analyzable through fast, reproducible, and auditable workflows. We report a working version of two of its layers, data curation and agentic orchestration, built and tested end to end on MINERvA open data. The guiding lesson throughout is that a cross section is a measurement, and not just a plotted shape, only if it carries a defensible systematic-uncertainty budget, a trustworthy unfolding, and a reproducible record. Using a single medium-energy playlist pair from the MINERvA open-data release (about $2.05\times10^{17}$ protons on target of data), we first reproduced the shapes of two published charged-current inclusive $\nu_\mu$ measurements through a complete extraction ladder: selection, background subtraction, D'Agostini unfolding, efficiency correction, and flux normalization. These shape-level reproductions ran and tracked the published results, but they lacked the systematic-uncertainty machinery that defines a MINERvA cross section. To supply it, we vendored and built the MINERvA Analysis Toolkit and developed a many-universe systematic-uncertainty tool that produces a portable covariance artifact, a parallel event-loop runner, and a per-run auditability harness. Validated against a published covariance release, the toolchain reproduces the released statistical, flux, and muon-energy-scale terms and shows that they account for roughly 63\% of the total variance, with the remainder unreleased. Using this same infrastructure, we then performed a measurement of our own design, the hadronic recoil-energy distribution of low-energy ($E_\nu<2.5$~GeV) charged-current inclusive events, and found data/simulation shape agreement of $\chi^2/\mathrm{ndf}=1.26$. Together these results show that the platform supports original physics and not only reproductions.

Breaux, Auto [Tulane U. (main)]↗

DOE OSTI2026

Toward the Neutrino Discovery Platform: An Auditable, Uncertainty-Bearing Toolchain for MINERvA Open-Data Cross-Section Analysis

The Neutrino Discovery Platform (NDP) aims to accelerate DUNE-era science by making the neutrino program's existing datasets analyzable through fast, reproducible, and auditable workflows. We report a working version of two of its layers, data curation and agentic orchestration, built and tested end to end on MINERvA open data. The guiding lesson throughout is that a cross section is a measurement, and not just a plotted shape, only if it carries a defensible systematic-uncertainty budget, a trustworthy unfolding, and a reproducible record. Using a single medium-energy playlist pair from the MINERvA open-data release (about $2.05\times10^{17}$ protons on target of data), we first reproduced the shapes of two published charged-current inclusive $\nu_\mu$ measurements through a complete extraction ladder: selection, background subtraction, D'Agostini unfolding, efficiency correction, and flux normalization. These shape-level reproductions ran and tracked the published results, but they lacked the systematic-uncertainty machinery that defines a MINERvA cross section. To supply it, we vendored and built the MINERvA Analysis Toolkit and developed a many-universe systematic-uncertainty tool that produces a portable covariance artifact, a parallel event-loop runner, and a per-run auditability harness. Validated against a published covariance release, the toolchain reproduces the released statistical, flux, and muon-energy-scale terms and shows that they account for roughly 63\% of the total variance, with the remainder unreleased. Using this same infrastructure, we then performed a measurement of our own design, the hadronic recoil-energy distribution of low-energy ($E_\nu<2.5$~GeV) charged-current inclusive events, and found data/simulation shape agreement of $\chi^2/\mathrm{ndf}=1.26$. Together these results show that the platform supports original physics and not only reproductions.

Breaux, Auto [Tulane U. (main)]↗

DOE OSTI2026

ORCHID: Orchestrated Retrieval-Augmented Classification of High-Risk Property with Intelligent Decision-Making

High-Risk Property (HRP) classification is critical at U.S. Department of Energy (DOE) sites, where inventories include sensitive and often dual-use equipment. Compliance must track evolving rules designated by various export control policies to make transparent and auditable decisions. Traditional expert-only workflows are time-consuming, backlog-prone, and struggle to keep pace with shifting regulatory boundaries. We propose ORCHID, a modular agentic framework for HRP classification that pairs retrieval-augmented generation (RAG) with human oversight to produce policy based outputs that can be audited. Small cooperating agents—retrieval, description refiner, classifier, validator, and feedback logger—coordinate via agent-to-agent messaging and invoke tools through the Model Context Protocol (MCP) for model-agnostic on-premise operation. The interface follows an "Item to Evidence to Decision" loop with step-by-step reasoning, on-policy citations, and append-only audit bundles (run-cards, prompts, evidence). In preliminary tests on real HRP cases, ORCHID improves accuracy and traceability over a non-agentic baseline while deferring uncertain items to Subject Matter Experts (SMEs). The demonstration shows single item submission, grounded citations, SME feedback capture, and exportable audit artifacts—illustrating a practical path to trustworthy LLM assistance in sensitive DOE compliance workflows.

Das, Sanjay [ORNL] (ORCID:0009000542591915)↗

DOE OSTI2026

V-HAMSTeR v1.0.0

V-HAMSTeR is a bioinformatics software tool designed to predict the hosts of viruses directly from genomic sequences. It can be used by researchers to predict animal, prokaryotic, plant, protist or fungal viral hosts including viruses that may be fragmented or discovered in environmental metagenomic datasets. Features & Uses: The software employs a novel dual-stream deep learning architecture that dynamically fuses implicit sequence embeddings from a genomic foundation model with 13 explicit, handcrafted biological features (e.g., coding density and strand switch rates). To ensure maximum reliability, V=HAMSTeR deploys a 5-fold deep ensemble calibrated via Joint Temperature Scaling, providing users with statistically rigorous confidence probabilities. It also features an automated sequence chunking and mean-pooling module to seamlessly process variable-length contigs. Advantages Over Similar Technologies: Existing tools (e.g., IPEV, RNAVirHost) typically rely on either basic k-mers or isolated neural networks. V-HAMSTeR's hybrid architecture captures both broad genomic context and specific biological motifs that standalone foundation models often miss. Furthermore, unlike competitor tools that struggle with incomplete data or exhibit extreme overconfidence, V-HAMSTeR is explicitly benchmarked and mathematically calibrated for fragmented assemblies (1kb–10kb). This makes it uniquely robust, accurate, and trustworthy for the messy reality of real-world environmental viromics.

Grigson, Susie [Lawrence Berkeley National Laborat↗

DOE OSTI2024

Cybersecurity Lessons Learned from Vehicle to Grid Engagement

As the transportation industry continues to become electrified, introduction of additional digital devices within associated actions such as recharging bring additional potential for cybersecurity attacks. Devices that are designed, implemented, and operated with cybersecurity as a crucial consideration exacerbate these concerns by failing to provide strict boundaries on access to and use of the equipment. Emerging use cases such as Vehicle to Grid (V2G) charging may expand the potential physical effects of a cybersecurity attack by providing indirect access to electrical components of a building microgrid or portions of the larger power grid. This paper serves as an overview of findings and recommendations based on cybersecurity testing performed at a V2G implementation site operated by a member of the Memorandum of Understanding (MOU) to Establish the Vehicle-to-Everything (V2X) Collaboration [1]. The Department of Energy Office of Cybersecurity, Energy Security, and Emergency Response is a signatory of the MOU, and has funded this research paper and associated body of work regarding V2X cybersecurity. Sandia has a large background of previous research focused on Electric Vehicle (EV) cybersecurity, such as reference [2], which includes an overall survey of EV infrastructure cybersecurity and recommendations based on those findings. This report seeks to expand knowledge of EV cybersecurity status and needs by focusing on a specific implementation of V2G charging, and providing recommendations based on the relevant findings. This report serves as a publicly available, sanitized description of applied vulnerability testing on an operational V2G implementation. A more in-depth technical version of the report is provided to the MOU partner, but not available at the time of writing due to inclusion of proprietary information. V2G charging comes with many research problems that must be solved before the technology can securely implemented in sites with unrestricted public access or where cybersecurity attacks could have increased consequences, such as government offices. V2G charging requires many stakeholders such as end users, host sites, equipment vendors, and integrators, which all rely on operational safety and security as well as security and trustworthiness of any associated financial transactions.

33 ADVANCED PROPULSION SYSTEMS↗