Towards Trustworthy Data-Driven Closure Models - Incorporating Input and Output Uncertainties in Neural Networks
Explore the source record for details and available documents.
Smith, Paul Andrew [Sandia National Laboratories (↗
SEARCH · Engineering Papers
Results for “trustworthiness”
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Toward Trustworthy Detectors Detector Characterization for SuperCDMS SNOLAB Commissioning
SuperCDMS SNOLAB is a next generation direct detection experiment searching for low mass dark matter using cryogenic germanium and silicon detectors operated at millikelvin temperatures. As commissioning begins, establishing stable, predictable detector response to energy deposits is a prerequisite for future physics analysis. This work studies detector stability and calibration for four SuperCDMS SNOLAB detectors, det 7 and det 15 (germanium) and det 11 and det 14 (silicon), using Barium-133 calibration data (356 keV gamma ray reference) and low background data (ambient radiation, no external source). The Ba-133 data show no distinct line at the expected energy, and the low background data show a baseline that drifts and oscillates rather than remaining flat, consistently across multiple channels, suggesting a shared, detector wide cause. These observations point to the cryogenic support system as the likely source, since small temperature fluctuations could couple into the temperature sensitive detectors, informing the ongoing commissioning effort.
O'Hanlon, Vika [Skidmore Coll.]↗
Scalable workflow for evaluating and optimizing large language models
This work describes the improved workflow for evaluating open-source large language models (LLMs) for trustworthiness. The workflow facilitates the acquisition of LLMs, the generation of LLM responses, and the evaluation of the responses for their trustworthiness. As a use case, the workflow is employed to evaluate dense, quantized, and pruned Meta Llama3.1 LLMs for their truthfulness. The outcome of the project could set the stage for understanding and developing trustworthy models in the future projects.
97 MATHEMATICS AND COMPUTING↗
Ecosystems for Scientific Computing in the Age of AI
Scientific computing is at an inflection point. Artificial intelligence (AI) is reshaping how scientific software is developed, how teams collaborate, how projects are governed, and how the next generation is trained. Drawing on insights from a 2025 workshop report, this article argues that the future of discovery will depend on agile, robust ecosystems built through socio-technical co-design—the intentional integration of technical and human systems. This perspective is essential for ensuring that future scientific computing remains trustworthy, sustainable, and scalable. It combines advances in AI, high-performance computing, and software with new models for cross-disciplinary collaboration, education, and workforce development. Key recommendations include building modular, trustworthy AI-enabled software ecosystems; enabling teams to integrate AI into scientific workflows while preserving human creativity, integrity, and rigor; and developing adaptive training pathways that keep pace with rapid technological change. By sharing these perspectives, we hope to stimulate broader community dialogue and encourage coordinated action.
AI↗
ChatBLAS: The First AI-Generated and Portable BLAS Library
We present ChatBLAS, the first AI-generated and portable Basic Linear Algebra Subprograms (BLAS) library on different CPU/GPU configurations. The purpose of this study is (i) to evaluate the capabilities of current large language models (LLMs) to generate a portable and HPC library for BLAS operations and (ii) to define the fundamental practices and criteria to interact with LLMs for HPC targets to elevate the trustworthiness and performance levels of the AI-generated HPC codes. The generated C/C++ codes must be highly optimized using device-specific solutions to reach high levels of performance. Additionally, these codes are very algorithm-dependent, thereby adding an extra dimension of complexity to this study. We used OpenAI’s LLM ChatGPT and focused on vector-vector BLAS level-1 operations. ChatBLAS can generate functional and correct codes, achieving high-trustworthiness levels, and can compete or even provide better performance against vendor libraries.
Valero Lara, Pedro↗
ChatMPI: LLM-Driven MPI Code Generation for HPC Workloads
The Message Passing Interface (MPI) standard plays a crucial role in enabling scientific applications for parallel computing and is an essential component in high-performance computing (HPC). However, implementing MPI code manually—especially applying a proper domain decomposition and communication pattern—is a challenging and error-prone task. We present ChatMPI, an AI assistant for MPI parallelization of sequential C codes. In our analysis, we focus on testing six essential HPC workloads, which are based on Basic Linear Algebra Subprograms levels 1, 2, and 3 as well as sparse, stencil, and iterative operations. We analyze the process of creating ChatMPI by using the ChatHPC library. This lightweight large language model (LLM)–based infrastructure enables HPC experts to efficiently create and supervise trustworthy AI capabilities for critical HPC software tasks. We study the data required for training (fine-tuning) ChatMPI to generate parallel codes that not only use MPI syntax correctly but also apply HPC techniques to reduce memory communication and maximize performance by using proper work decomposition. With a relatively small training dataset composed of a few dozen prompts and fewer than 15 minutes of fine-tuning on one node equipped with two NVIDIA H100 GPUs, ChatMPI elevates trustworthiness for MPI code generation of current LLMs (e.g., Code Llama, ChatGPT-4o and ChatGPT 5). Additionally, we evaluate the performance of the MPI codes generated by ChatMPI in comparison with the ones generated by ChatGPT-4o and ChatGPT-5. The codes generated by ChatMPI provide up to a 4 × boost in performance by using better problem decomposition, communication patterns, and HPC techniques (e.g., communication avoiding).
Valero Lara, Pedro [ORNL] (ORCID:0000000214794310)↗
Trust-Based Detection and Mitigation of Cyber Attacks in Distributed Cooperative Control of Islanded AC Microgrids
In this study, we address the challenge of detecting and mitigating cyber attacks in the distributed cooperative control of islanded AC microgrids, with a particular focus on detecting False Data Injection Attacks (FDIAs), a significant threat to the Smart Grid (SG). The SG integrates traditional power systems with communication networks, creating a complex system with numerous vulnerable links, making it a prime target for cyber attacks. These attacks can lead to the disclosure of private data, control network failures, and even blackouts. Unlike machine learning-based approaches that require extensive datasets and mathematical models dependent on accurate system modeling, our method is free from such dependencies. To enhance the microgrid’s resilience against these threats, we propose a resilient control algorithm by introducing a novel trustworthiness parameter into the traditional cooperative control algorithm. Our method evaluates the trustworthiness of distributed energy resources (DERs) based on their voltage measurements and exchanged information, using Kullback-Leibler (KL) divergence to dynamically adjust control actions. We validated our approach through simulations on both the IEEE-34 bus feeder system with eight DERs and a larger microgrid with twenty-two DERs. The results demonstrated a detection accuracy of around 100%, with millisecond range mitigation time, ensuring rapid system recovery. Additionally, our method improved system stability by up to almost 100% under attack scenarios, showcasing its effectiveness in promptly detecting attacks and maintaining system resilience. These findings highlight the potential of our approach to enhance the security and stability of microgrid systems in the face of cyber threats.
Computer Science↗
On the Need to Align Intent and Implementation in Uncertainty Quantification for Machine Learning
Quantifying uncertainties for machine learning (ML) models is a foundational challenge in modern data analysis. This challenge is compounded by at least two key aspects of the field: (a) inconsistent terminology surrounding uncertainty and estimation across disciplines, and (b) the varying technical requirements for establishing trustworthy uncertainties in diverse problem contexts. In this position paper, we aim to clarify the depth of these challenges by identifying these inconsistencies and articulating how different contexts impose distinct epistemic demands. We examine the current landscape of estimation targets (e.g., prediction, inference, simulation-based inference), uncertainty constructs (e.g., frequentist, Bayesian, fiducial), and the approaches used to map between them. Drawing on the literature, we highlight and explain examples of problematic mappings. To help address these issues, we advocate for standards that promote alignment between the \textit{intent} and \textit{implementation} of uncertainty quantification (UQ) approaches. We discuss several axes of trustworthiness that are necessary (if not sufficient) for reliable UQ in ML models, and show how these axes can inform the design and evaluation of uncertainty-aware ML systems. Our practical recommendations focus on scientific ML, offering illustrative cases and use scenarios, particularly in the context of simulation-based inference (SBI).
Trivedi, Shubhendu [MIT] (ORCID:0000000312374301)↗
Trusted Simulation: Considering Model Quality in the Context of User Trust
A high‐quality simulation model should help its users to easily and appropriately calibrate their trust in the model. Traditional evaluation metrics such as validation and robustness are necessary but insufficient for this task. Trust calibration depends on factors like the model's transparency, applicability to intended use, usability, reputation, and consideration of potential bias. This article proposes a framework for designing and evaluating system dynamics models by considering factors that contribute to the proper calibration of user trust. This framework takes inspiration from trusted artificial intelligence, broadening our traditional concept of model quality and explicitly focusing on what users need to consider a model trustworthy and to understand the model's relevance to its intended purpose. The trusted simulation framework can improve our integration of model quality activities throughout the modeling process, leading to more impactful and better‐targeted model design, development, and evaluation.
Naugle, Asmeret Bier [Sandia National Laboratories↗
Enabling end-to-end secure federated learning in biomedical research on heterogeneous computing environments with APPFLx
Facilitating large-scale, cross-institutional collaboration in biomedical machine learning (ML) projects requires a trustworthy and resilient federated learning (FL) environment to ensure that sensitive information such as protected health information is kept confidential. Specifically designed for this purpose, this work introduces APPFLx - a low-code, easy-to-use FL framework that enables easy setup, configuration, and running of FL experiments. APPFLx removes administrative boundaries of research organizations and healthcare systems while providing secure end-to-end communication, privacy-preserving functionality, and identity management. Furthermore, it is completely agnostic to the underlying computational infrastructure of participating clients, allowing an instantaneous deployment of this framework into existing computing infrastructures. Experimentally, the utility of APPFLx is demonstrated in two case studies: (1) predicting participant age from electrocardiogram (ECG) waveforms, and (2) detecting COVID-19 disease from chest radiographs. Here, ML models were securely trained across heterogeneous computing resources, including a combination of on-premise high-performance computing and cloud computing facilities. By securely unlocking data from multiple sources for training without directly sharing it, these FL models enhance generalizability and performance compared to centralized training models while ensuring data remains protected. In conclusion, APPFLx demonstrated itself as an easy-to-use framework for accelerating biomedical studies across organizations and healthcare systems on large datasets while maintaining the protection of private medical data.
Biomedical Research↗
Resilient information and inference networks under mixed-trust sensing
With ubiquitous digitization, sensing, and computational intelligence deployed in increasingly more and broader domains, including critical infrastructure, potentially misleading and destabilizing effects of multimodal anomalies and adversarial behavior are growing in importance. Here, we develop randomized and reinforcement learning-based strategies for strategically recruiting and utilizing deployed (and, thus, vulnerable and potentially faulty and/or compromised) nodes from information and inference networks, while defending against adversaries that attempt to misguide assessments of inferred variables. Recognizing that, besides communication and other costs, sampling from any observable node can either provide true data or dangerously expose our inference to misinformation (without being easily distinguishable what actually happens), the proposed strategies proceed by progressively recruiting nodes and cautiously scaling their information contribution based on assumed, or, in our reinforcement learning approach, intelligently weighed trustworthiness, with the learning approach also considering network-wide, threat-inclusive risk/value tradeoffs. While avoiding the hardware, communication, analytical and computational burden of explicit redundancy, the proposed defensive schemes enable on-the-fly assessments of underlying processes, and system-wide situational awareness with demonstrable resilience against adversarial activities.
97 - MATHEMATICS AND COMPUTING↗
AI-assisted object condensation clustering for calorimeter shower reconstruction at CLAS12
Several nuclear physics studies using the CLAS12 detector rely on the accurate reconstruction of neutrons and photons from its forward angle calorimeter system. These studies often place restrictive cuts when measuring neutral particles due to an overabundance of false clusters created by the existing calorimeter reconstruction software. In this work, we present a new AI approach to clustering CLAS12 calorimeter hits based on the object condensation framework. The model learns a latent representation of the full detector topology using GravNet layers, serving as the positional encoding for an event’s calorimeter hits which are processed by a Transformer encoder. This unique structure allows the model to contextualize local and long range information, improving its performance. Evaluated on one million simulated $e^-$ $+$ $p$ collision events, our method significantly improves cluster trustworthiness: the fraction of reliable neutron clusters, increasing from 8.88% to 30.73%, and photon clusters, increasing from 51.07% to 64.73%. In conclusion, our study also marks the first application of AI clustering techniques for hodoscopic detectors, showing potential for usage in many other experiments.
Calorimeters↗
Advanced surrogate model for electron-scale turbulence in tokamak pedestals
We derive an advanced surrogate model for predicting turbulent transport at the edge of tokamaks driven by electron temperature gradient (ETG) modes. Our derivation is based on a recently developed sensitivity-driven sparse grid interpolation approach for uncertainty quantification and sensitivity analysis at scale, which informs the set of parameters that define the surrogate model as a scaling law. Our model reveals that ETG-driven electron heat flux is influenced by the safety factor q, electron beta β e and normalized electron Debye length λ D , in addition to well-established parameters such as the electron temperature and density gradients. To assess the trustworthiness of our model's predictions beyond training, we compute prediction intervals using bootstrapping. The surrogate model's predictive power is tested across a wide range of parameter values, including within-distribution testing parameters (to verify our model) as well as out-of-bounds and out-of-distribution testing (to validate the proposed model). Overall, validation efforts show that our model competes well with, or can even outperform, existing scaling laws in predicting ETG-driven transport.
fusion plasma↗
Machine learning-accelerated discovery of heat-resistant polysulfates for electrostatic energy storage
The development of heat-resistant dielectric polymers that withstand intense electric fields at high temperatures is critical for electrification. Balancing thermal stability and electrical insulation, however, is exceptionally challenging as these properties are often inversely correlated. A traditional intuition-driven polymer design approach results in a slow discovery loop that limits breakthroughs. Here we present a machine learning-driven strategy to rapidly identify high-performance, heat-resistant polymers. A trustworthy feed-forward neural network is trained to predict key proxy parameters and down select polymer candidates from a library of nearly 50,000 polysulfates. The highly efficient and modular sulfur fluoride exchange click chemistry enables successful synthesis and validation of selected candidates. A polysulfate featuring a 9,9-di(naphthalene)-fluorene repeat unit exhibits excellent thermal resilience and achieves ultrahigh discharged energy density with over 90% efficiency at 200 °C. Its exceptional cycling stability underscores its promise for applications in demanding electrified environments.
Li, He↗
AutoLabs: cognitive multi-agent systems with self-correction for autonomous chemical experimentation
The automation of chemical research through self-driving laboratories (SDLs) promises to accelerate scientific discovery, yet the reliability and granular performance of the underlying AI agents remain critical, under-examined challenges. In this work, we introduce AutoLabs, a self-correcting, multi-agent architecture designed to autonomously translate natural-language instructions into executable protocols for a high-throughput liquid handler. The system engages users in dialogue, decomposes experimental goals into discrete tasks for specialized agents, performs tool-assisted stoichiometric calculations, and iteratively self-corrects its output before generating a hardware-ready file. We present a comprehensive evaluation framework featuring five benchmark experiments of increasing complexity, from simple sample preparation to multi-plate timed syntheses. Through a systematic ablation study of 20 agent configurations, we assess the impact of reasoning capacity, architectural design (single- vs. multi-agent), tool use, and self-correction mechanisms. Our results demonstrate that agent reasoning capacity is the most critical factor for success, reducing quantitative errors in chemical amounts (nRMSE) by over 85% in complex tasks. When combined with a multi-agent architecture and iterative self-correction, AutoLabs approaches expert-authored reference procedures on the benchmark (F1-score > 0.89) on challenging multi-plate syntheses. These findings establish a clear blueprint for developing robust and trustworthy AI partners for autonomous laboratories, highlighting the synergistic effects of modular design, advanced reasoning, and self-correction to ensure both performance and reliability in high-stakes scientific applications. Code: https://github.com/pnnl/autolabs
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
Automated structural analysis of small angle scattering data from common nanoparticles via machine learning
A data-efficient and trustworthy machine learning approach is developed for automated inverse analysis of small angle scattering data.
Roberts, Graham [School of Computing, University o↗
Experimental uncertainty quantification using templates of expected measurement uncertainties for fast neutron-induced total, capture, and scattering cross sections
Careful experimental uncertainty quantification (UQ) is key for developing trustworthy evaluated nuclear data. Templates to account for missing or under-reported experimental uncertainties were recently developed by the covariance committee of Cross Section Evaluation Working Group (CSEWG). In this work, we illustrate the practical application and limitations of these templates for selected neutron-induced reactions, including (n, tot), (n, γ), and (n, xn) in the fast energy range, to illustrate their use in data analyses for nuclear data evaluations. We show that while the templates provide consistent framework, proper implementation still requires detailed knowledge of experimental conditions and careful treatment of nonlinear effects in cross section derivation. Case studies highlight how template-assisted UQ improves consistency with previous evaluations such as ENDF/B and reveals open challenges in propagating uncertainties across different energy regimes. The main contribution of this paper is to connect formal template recommendations with their use in practical evaluation workflows, clarifying both their benefits and current limitations.
73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
Dynamic in-context learning with conversational models for data extraction and materials property prediction
The advent of natural language processing and large language models (LLMs) has revolutionized the extraction of data from unstructured scholarly papers. However, ensuring data trustworthiness remains a significant challenge. In this paper, we introduce PropertyExtractor, an open-source tool that leverages advanced conversational LLMs such as Google gemini-pro and OpenAI gpt-4, blends zero-shot with few-shot in-context learning, and employs engineered prompts for the dynamic refinement of structured information hierarchies—enabling autonomous, efficient, scalable, and accurate identification, extraction, and verification of material property data. Our tests on material data demonstrate precision and recall that exceed 95% with an error rate of ∼9%, highlighting the effectiveness and versatility of the toolkit. Finally, databases for 2D material thicknesses, a critical parameter for device integration, and energy bandgap values are developed using PropertyExtractor. In particular, for the thickness database, the rapid evolution of the field has outpaced both experimental measurements and computational methods, creating a significant data gap. Our work addresses this gap and showcases the potential of PropertyExtractor as a reliable and efficient tool for the autonomous generation of various material property databases, advancing the field.
Ekuma, Chinedu E. (ORCID:0000000258527556)↗