Toward Certifying Trustworthy Machine Learning
Explore the source record for details and available documents.
Darling, Michael Christopher [Sandia National Labo↗
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.
Sandia's Journey toward Trustworthy and Efficient Foundation Models
Explore the source record for details and available documents.
Newcomer, Justin T [Sandia National Laboratories (↗
Model-form uncertainty for trustworthy predictions
Poster to be presented at IMSI workshop Uncertainty Quantification and Machine Learning for Complex Physical Systems
Bandy, Rileigh Jade [Sandia National Laboratories ↗
Toward Trustworthy Autonomous Science: A Two-Year Community Roadmap
One year ago, the AISLE roadmap argued that autonomous laboratories operated as isolated islands and proposed a grassroots network organized around five critical dimensions. The field has since moved faster than that roadmap anticipated: multi-agent systems have produced experimentally validated hypotheses, self-driving laboratories have grown more interoperable and orchestrated, reasoning-trained and domain foundation models have raised the capability ceiling, and the Genesis Mission has placed autonomous experimentation at the center of U.S. federal science strategy, with industry emerging as a primary actor. Progress has met a sobering counter-current, including a corrected flagship discovery result, benchmarks showing that agents which rival experts on closed-ended questions still complete only a fraction of open-ended research, and fabricated citations surfacing at leading venues. We read this as the defining tension of the field: producing a candidate discovery is no longer the hard part, but verifying it is, and this asymmetry now limits autonomous science more than raw model capability. Accordingly, we update the roadmap around seven dimensions, revisiting the original five and elevating two former cross-cutting concerns, trust, verification, and reproducibility, and safety, security, and governance, to first-class status. We assess the original milestones (M1 through M14) as achieved, partially achieved, reframed, or open, add four new milestones (M15 through M18) for the elevated dimensions, and scope the path forward to a two-year horizon, with the first year concentrating on interfaces, protocol adoption, and the scaffolding of verification, and the second targeting federation, zero-trust coordination, and governance. Throughout, we position the grassroots network as the interoperability fabric that lets national programs, international initiatives, and commercial platforms connect rather than re-silo.
99 GENERAL AND MISCELLANEOUS↗
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 (↗
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.]↗
Building Trustworthy Machine Learning Models for Astronomy
Astronomy is entering an era of data-driven discovery, due in part to modern machine learning (ML) techniques enabling powerful new ways to interpret observations. This shift in our scientific approach requires us to consider whether we can trust the black box. Here, we overview methods for an often-overlooked step in the development of ML models: building community trust in the algorithms. Trust is an essential ingredient not just for creating more robust data analysis techniques, but also for building confidence within the astronomy community to embrace machine learning methods and results.
46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
Parsimonious Inference Foundations for Trustworthy-by-Design Machine Learning.
Abstract not provided.
Duersch, Jed Alma↗
Dynamic Model Agnostic Reliability Evaluation of Machine-Learning Models Integrated in Instrumentation & Control Systems
In recent years, the field of machine learning (ML), specifically neural networks, has grown significantly and has spurred research in its applicability to digital instrumentation and control systems (DI&C). While ML models have shown promise in operational contexts, the trustworthiness of using such algorithms has not been adequately assessed. Failures of ML integrated systems are not well understood, and the lack of comprehensive risk modeling can degrade the trustworthiness in these systems. In recent reports by the National Institute for Standards and Technology (NIST) [1] and the Nuclear Regulatory Commission (NRC) [2], they indicate that trustworthiness in ML is a critical barrier and will play a vital role in the safe, accountable, and secure operation of intelligent systems. Thus, in this work, we demonstrate a dynamic model-agnostic method to quantify the relative reliability of AI/ML predictions by incorporating out-of-distribution (OOD) detection on the training dataset. It is well documented that most ML algorithms excel at interpolation (or near-interpolation) tasks but experience significant performance degradation at extrapolation. The method, referenced as the Laplacian distributed decay for reliability (LADDR), determines the difference between the operational and training datasets which can used to the relative reliability of AI/ML predictions. LADDR is then demonstrated on a feedforward neural network based digital twin used for the prediction of safety significant factors during a loss-of-flow transient. LADDR is used to demonstrate how training data can be used as evidence to support the relative reliability of ML/AI predictions enhancing the overall trustworthiness of the system.
46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
Dynamic Model Agnostic Reliability Evaluation of Machine-Learning Models Integrated in Instrumentation & Control Systems
In recent years, the field of data-driven neural network-based machine learning (ML) algorithms has grown significantly and spurred research in its applicability to instrumentation and control systems. While they are promising in operational contexts, the trustworthiness of such algorithms is not adequately assessed. Failures of ML-integrated systems are poorly understood; the lack of comprehensive risk modeling can degrade the trustworthiness of these systems. In recent reports by the National Institute for Standards and Technology, trustworthiness in ML is a critical barrier to adoption and will play a vital role in intelligent systems' safe and accountable operation. Thus, in this work, we demonstrate a real-time model-agnostic method to evaluate the relative reliability of ML predictions by incorporating out-of-distribution detection on the training dataset. It is well documented that ML algorithms excel at interpolation (or near-interpolation) tasks but significantly degrade at extrapolation. This occurs when new samples are "far" from training samples. The method, referred to as the Laplacian distributed decay for reliability (LADDR), determines the difference between the operational and training datasets, which is used to calculate a prediction's relative reliability. LADDR is demonstrated on a feedforward neural network-based model used to predict safety significant factors during different loss-of-flow transients. LADDR is intended as a "data supervisor" and determines the appropriateness of well-trained ML models in the context of operational conditions. Ultimately, LADDR illustrates how training data can be used as evidence to support the trustworthiness of ML predictions when utilized for conventional interpolation tasks.
97 MATHEMATICS AND COMPUTING↗
Clarifying trust of materials property predictions using neural networks with distribution-specific uncertainty quantification
It is critical that machine learning (ML) model predictions be trustworthy for high-throughput catalyst discovery approaches. Uncertainty quantification (UQ) methods allow estimation of the trustworthiness of an ML model, but these methods have not been well explored in the field of heterogeneous catalysis. Herein, we investigate different UQ methods applied to a crystal graph convolutional neural network to predict adsorption energies of molecules on alloys from the Open Catalyst 2020 dataset, the largest existing heterogeneous catalyst dataset. We apply three UQ methods to the adsorption energy predictions, namely k-fold ensembling, Monte Carlo dropout, and evidential regression. The effectiveness of each UQ method is assessed based on accuracy, sharpness, dispersion, calibration, and tightness. Evidential regression is demonstrated to be a powerful approach for rapidly obtaining tunable, competitively trustworthy UQ estimates for heterogeneous catalysis applications when using neural networks. Recalibration of model uncertainties is shown to be essential in practical screening applications of catalysts using uncertainties.
36 MATERIALS SCIENCE↗
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↗
Considerations when Implementing Shift Work in Nuclear Operations
Many domestic and international nuclear facilities have processes that require personnel to work on some type of shift. Shift work has many different schedules such as night, morning, swing, and rotating shift. Some common shifts are DuPont, Pitman, and Panama. There are many psychological and physiological impacts to a person working shifts. These impacts can affect work performance, safety, and security within an organization. A well-established nuclear organization relies on a strong security culture that implements a trustworthiness or reliability program. The IAEA defines this type of program as individuals meeting the highest standards of reliability, trustworthiness, and physical and mental suitability. Psychological and physiological impacts that apply to a Trustworthiness Program are reliability (an individual’s ability to adhere to security and safety rules and regulations) and physical and mental suitability. If shift work isn’t properly implemented in Facility Operations, then several issues or human factors can arise. An employee that suffers from a poorly designed shift, gets overworked, or doesn’t have the proper rest period implemented, may suffer from shift work disorder, acute fatigue, or cumulative fatigue. Introducing fatigue into Facility Operations can have severe consequences to security, safety, production, and cost. Another challenge of shiftwork within a facility is laziness and complacency. Creating an atmosphere where the employee is willing to admit fatigue to his or her supervisor is a challenge. It is up to the organization to do the needed research on shift work and to implement the best shift for their facility and personnel.
Stockwell, Brandon↗
Explainable Artificial Intelligence Technology for Predictive Maintenance
The domestic nuclear power plant fleet has relied on labor-intensive and time-consuming preventive maintenance programs, thus driving up operation and maintenance costs to achieve high-capacity factors. Artificial intelligence and machine learning can help simplify complex problems, such as diagnosing equipment degradation, to enable more effective decision-making. Benefits will be felt not only within existing analog and digital instrumentation and control, but also work processes, the integration of people with technology, and most importantly, the business case. Together, these hold promise to make nuclear power more efficient and reduce costs associated with operation and maintenance. While the artificial intelligence and machine learning technologies hold significant promise in the nuclear industry, there are challenges or barriers to their adoption. This report outlines the those different machine learning adoption barriers (categorized as historical, technical, economic, regulatory, and user) that the industry must overcome to realize the full benefits of artificial intelligence and machine learning capabilities for long-term economic sustainability. This report also provides solutions for some of these barriers by focusing on improving the explainability of machine learning to encourage trust from the end-user. Trust and explainability are essential to machine learning adoption. This report focuses on research-developed solutions to some of these barriers while analyzing a non-safety-related system, namely the circulating water system. This system frequently experiences waterbox fouling which our models preemptively diagnoses then explains to the operator how those conclusions were reached. This report presents and discusses the inherent trade-off between machine learning performance (in terms of accuracy) and explainability, where highly accurate machine learning methods (such as deep-learning) are the least explainable, and the most explainable methods (such as decision trees) are the least accurate. In addition, explainability of artificial intelligence techniques in terms of transparency and post-hoc metrics are discussed. This report outlines the importance of data novelty and value of new information in evaluating both the explainability and trustworthiness. Novelty detection helps to establish consistency or inconsistency of the new data with respect to the training data. On the other hand, value of information could be a part of the user-centric visualization recommendation system that request additional information to be collected, thereby strengthening the machine learning outcomes. During this project, a copyrighted user-centric visualization that aligns with a human-in-the-loop approach was developed. The user-centric visualization presents different levels of information and can be tailored as per user credentials to gain user confidence. One of the salient features of the user-centric visualization is it presents machine learning methods with explainability metrics. A simplified version of the user-centric visualization was presented to 32 users with varying levels of machine learning expertise. Feedback was solicited to test the hypothesis that the app contained sufficient explainability and that the users would trust the algorithm. Overall, the app was positively received, and the hypothesis was supported. This report discusses the trust-but-verify framework – a potential approach to build user trust artificial intelligence. The framework discusses trust from the human level to artificial intelligence level. The fundamental premise of the trust but verify framework is derived from an observation of nuclear safety culture (i.e., nuclear power plant personnel do not rely on a singular source of data to make a decision). This also ties back to the user-centric visualization that presents different levels of information to achieve both explainability and trustworthiness of artificial intelligence. Even so, the adoption of artificial intelligence and machine learning in the nuclear industry faces additional barriers, namely regulatory and stakeholder readiness. To overcome these challenges, new solutions must gain regulatory approval and cater to stakeholder needs. The Nuclear Regulatory Committee has a 5-year strategic plan which prepares them for reviewing artificial intelligence technologies in licensee submissions. Early and frequent engagement with the regulator is encouraged. Additionally, artificial intelligence solutions should incorporate human-in-the-loop considerations and offer explainability. Stakeholders must prepare by hiring or training staff to adapt to advancing technology in everyday plant tasks.
22 GENERAL STUDIES OF NUCLEAR REACTORS↗
Extreme sparsification of physics-augmented neural networks for interpretable model discovery in mechanics
Data-driven constitutive modeling with neural networks has received increased interest in recent years due to its ability to easily incorporate physical and mechanistic constraints and to overcome the challenging and time-consuming task of formulating phenomenological constitutive laws that can accurately capture the observed material response. However, even though neural network-based constitutive laws have been shown to generalize proficiently, the generated representations are not easily interpretable due to their high number of trainable parameters. Sparse regression approaches exist that allow for obtaining interpretable expressions, but the user is tasked with creating a library of model forms which by construction limits their expressiveness to the functional forms provided in the libraries. Here, in this work, we propose to train regularized physics-augmented neural network-based constitutive models utilizing a smoothed version of $L^0$-regularization. This aims to maintain the trustworthiness inherited by the physical constraints, but also enables interpretability which has not been possible thus far on any type of machine learning-based constitutive model where model forms were not assumed a priori but were actually discovered. During the training process, the network simultaneously fits the training data and penalizes the number of active parameters, while also ensuring constitutive constraints such as thermodynamic consistency. We show that the method can reliably obtain interpretable and trustworthy constitutive models for compressible and incompressible hyperelasticity, yield functions, and hardening models for elastoplasticity, using synthetic and experimental data. This work aims to set a new paradigm for interpretable machine learning models in the broad area of solid mechanics where low and limited data is available along with prior knowledge of physical constraints that the learned maps need to obey. This paradigm can potentially be extended to a broader spectrum of scientific exploration.
Data-driven constitutive models↗
Demystifying Cyberattacks: Potential for Securing Energy Systems With Explainable AI : Preprint
Modernization of energy systems has led to in- creased interactions among multiple critical infrastructures and diverse stakeholders making the challenge of operational decision making more complex and at times beyond cognitive capabilities of human operators. The state-of-the-art machine learning and deep learning approaches show promise of supporting users with complex decision-making challenges, such as those occurring in our rapidly transforming cyber-physical energy systems. However, successful adoption of data-driven decision support technology for critical infrastructure will be dependent on the ability of these technologies to be trustworthy and contextually interpretable. In this paper, we investigate the feasibility of implementing XAI for interpretable detection of cyberattacks in the energy system. Leveraging a proof-of-concept simulation use case of detection of a data falsification attack on a photovoltaic system using XGBoost algorithm, we demonstrate how Local Interpretable Model-Agnostic Explanations (LIME), a flavor XAI approach, can help provide contextual and actionable interpretation of cyberattack detection.
artificial intelligence↗
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↗