Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “curation”

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.

At least 1,639 records · Page 91

FATHOMS-RAG: A Framework for the Assessment of Thinking and Observation in Multimodal Systems that use Retrieval Augmented Generation

Retrieval-augmented generation (RAG) has emerged as a promising paradigm for improving factual accuracy in large language models (LLMs). We introduce a benchmark designed to evaluate RAG pipelines as a whole, evaluating a pipelines ability to ingest several modalities of information. We present (1) a curated dataset of 93 questions designed to evaluate a pipeline's ability to ingest textual data, tables, images, multimodal data, and cross-document multimodal data; (2) a phrase-level recall metric for correctness; (3) a nearest-neighbor embedding classifier in an attempt to classify pipeline hallucinations; (4) a comparative evaluation of 2 pipelines built with open-source retrieval mechanisms and 4 closed-source foundational models; and (5) a third-party human evaluation of the alignment of our correctness and hallucination metrics. We find that closed-source pipelines significantly outperform open-source pipelines in both the correctness and halucination metrics, with a wider performance gap in questions relying on multimodal and cross-document information. We also find after a human evaluation of our correctness and hallucination metric compared with our questions and pipeline responses, average agreement was 4.62 for correctness 4.53 for hallucination detection on a 1-5 Likert scale with 5 being strongly agree with our determination.

Hildebrand, Samuel [ORNL] (ORCID:0009000465963104)↗

Thermal Performance of Spandrel Assemblies in Glazed Wall Systems: Laboratory Test Design – Challenges and Test Results

Accurate thermal performance calculation procedures for opaque spandrel areas in curtain wall and window wall systems are essential for rating systems when comparing spandrel systems. However, there is a lack of consensus in thermal modeling needed for accurately characterizing heat transfer through spandrel assemblies due to the complex arrangement of materials and structural components. Several studies indicate that conventional 2D thermal simulations may overestimate R-values by 30% compared to physical testing and 3D simulations. Detailed simulations and well-curated laboratory test data are necessary to build confidence in simulation models, which will later be used to develop correlations to improve widely used conventional 2D thermal simulations. This study aims to experimentally test heat transfer through various spandrel assemblies to validate 3D simulation models. Also, the challenges of conducting a thorough testing design along with the solutions would be documented. The team developed a design for testing spandrel assemblies, making appropriate modifications to the existing heat, air, and moisture (HAM) chamber to accommodate the testing needs. Two moveable baffles were designed and fabricated to guide airflow direction parallel to the test article surface. The data acquisition capabilities in the chamber were upgraded to add more than two hundred sensors to the climate and indoor side of the chamber. The goal is to provide a quality dataset for validating complex 3D modeling simulations, which will be used to develop improved thermal simulation techniques that more accurately represent the thermal behavior of spandrel assemblies and their integration within the building envelope. This paper will summarize the results for the boundary conditions of the testing and the temperature variation across different locations of the spandrel assemblies.

Kunwar, Niraj [ORNL] (ORCID:0000000263457652)↗

ON THE EFFECTIVENESS OF LLMS IN UNIT TEST GENERATION FOR STRUCTURED TEXT PROGRAMS

The reliability of industrial automation systems heavily depends on the correctness of Programmable Logic Controller (PLC) programs, which are often written in Structured Text (ST). While Large Language Models (LLMs) have shown promise in automating test generation for mainstream programming languages, their effectiveness for the syntactically strict ST language remains underexplored. This thesis presents a systematic empirical evaluation of three state-of-the-art LLMs—GPT-4o, Gemini 2.5 Pro, and Claude Sonnet 4.5—for generating ST unit tests. We examine three prompting strategies: Natural Language (NL), Code Language (CL), and Chain-of-Thought (CoT), across a curated set of 11 ST function blocks. The quality of the generated tests is assessed using Compilation Success Rate (CSR), Statement Coverage (SC), and Branch Coverage (BC). In the zero-shot setting, Claude Sonnet 4.5 achieves the highest CSR, while Gemini 2.5 Pro consistently delivers the best statement and branch coverage, particularly under CL prompts. By incorporating a one-shot CL prompt, all models exhibit substantial improvements—most notably GPT-4o, whose CSR increases from 45.45% to 90.91%, with substantial gains in both SC and BC. To further contextualize these findings, we compare GPT-4o’s one-shot results with PLCAutoTester, a state-ofthe- art ST unit test generation tool, on an additional benchmark dataset. While LLMgenerated tests approach competitive coverage levels, PLCAutoTester maintains significantly higher and more stable coverage across programs. This study provides the first comprehensive benchmark of modern LLMs for ST unit testing, highlighting their strengths, limitations, and improvements through one-shot prompting, and positioning their performance relative to specialized automated testing tools in industrial automation.

42 ENGINEERING↗

Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis

Operational safety in high-stakes domains such as industrial process control, autonomous, and safety-critical systems demand reliable hazard identification. While large language models (LLMs) have shown promise in automating safety analysis tasks, single-turn, monolithic inference is brittle: it lacks the self-correction, deliberation, and contextual refinement that safety engineers apply iteratively. In this paper, we introduce HAZDIAL, a framework that investigates whether structured agentic dialogue (multi-agent, multi-turn interactions) improves the quality of NLP-based hazard identification over single-pass baselines. We systematically compare two dialogue modalities: adversarial debate and constructive discussion, and propose an genetic algorithm-based agentic interaction optimization. We evaluate all configurations against a curated golden dataset using standard classification metrics (accuracy, precision, recall, F1) and a novel dialogue metrics. This work advances the intersection of dialogue systems, multi-agent reasoning, and AI safety, providing empirical evidence for dialogue-driven hazard analysis.

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

All Systems Go: Regional Collaborations for Scaling AEC Innovation: Preprint

The high and rising cost of preserving and delivering housing in the U.S. requires changes to existing practices of finance, design, and construction. Innovative methods such as industrialized construction could offer the means to address housing undersupply while reducing delivery costs, operational costs and material waste in the building industry, but they face challenges to success and to scale. Simultaneously, construction and cleantech innovators themselves face skepticism from the traditional entrepreneurial ecosystem such as incubators and accelerators while attempting to navigate systems level challenges. To respond to this need, various public and private sector stakeholders have launched initiatives to support innovative companies. These include nonprofits such as Terner Labs and Ivory Innovations offering curated programming to architecture, engineering, and construction (AEC) startups; housing developers in Minnesota and California "bundling" multiple projects together to reach economies of scale with a consistent project team; public and private sector entities developing "catalogues" of pre-approved home designs in the U.S. and Canada. This exploratory paper documents several of these emerging ecosystem-development efforts to support innovative housing approaches, characterizing them by leading stakeholder and intervention strategy based on publicly available information. The paper finds that these initiatives share similar high level goals but vary in implementation, reflecting different stakeholder priorities, regional market and policy dynamics, and housing typologies. The early stage of these efforts offer limited data for comparing actual outcomes, but the paper highlights common qualitative themes and identifies opportunities for further research and potential coordination among these efforts.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

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)]↗

Methods for assisting recovery of damaged brain and spinal cord and treating various diseases using arrays of x-ray microplanar beams

A method of assisting recovery of an injury site of the central nervous system (CNS) or treating a disease includes providing a therapeutic dose of X-ray radiation to a target volume through an array of parallel microplanar beams. The dose to treat CNS injury temporarily removes regeneration inhibitors from the irradiated site. Substantially unirradiated cells surviving between beams migrate to the in-beam portion and assist recovery. The dose may be staggered in fractions over sessions using angle-variable intersecting microbeam arrays (AVIMA). Additional doses are administered by varying the orientation of the beams. The method is enhanced by injecting stem cells into the injury site. One array or the AVIMA method is applied to ablate selected cells in a target volume associated with disease for palliative or curative effect. Atrial fibrillation is treated by irradiating the atrial wall to destroy myocardial cells while continuously rotating the subject.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Next Generation Models for Storage and Representation of Microbial Biological Annotation

Background Traditional genome annotation systems were developed in a very different computing era, one where the World Wide Web was just emerging. Consequently, these systems are built as centralized black boxes focused on generating high quality annotation submissions to GenBank/EMBL supported by expert manual curation. The exponential growth of sequence data drives a growing need for increasingly higher quality and automatically generated annotation. Typical annotation pipelines utilize traditional database technologies, clustered computing resources, Perl, C, and UNIX file systems to process raw sequence data, identify genes, and predict and categorize gene function. These technologies tightly couple the annotation software system to hardware and third party software (e.g. relational database systems and schemas). This makes annotation systems hard to reproduce, inflexible to modification over time, difficult to assess, difficult to partition across multiple geographic sites, and difficult to understand for those who are not domain experts. These systems are not readily open to scrutiny and therefore not scientifically tractable. The advent of Semantic Web standards such as Resource Description Framework (RDF) and OWL Web Ontology Language (OWL) enables us to construct systems that address these challenges in a new comprehensive way. Results Here, we develop a framework for linking traditional data to OWL-based ontologies in genome annotation. We show how data standards can decouple hardware and third party software tools from annotation pipelines, thereby making annotation pipelines easier to reproduce and assess. An illustrative example shows how TURTLE (Terse RDF Triple Language) can be used as a human readable, but also semantically-aware, equivalent to GenBank/EMBL files. Conclusions The power of this approach lies in its ability to assemble annotation data from multiple databases across multiple locations into a representation that is understandable to researchers. In this way, all researchers, experimental and computational, will more easily understand the informatics processes constructing genome annotation and ultimately be able to help improve the systems that produce them.

59 BASIC BIOLOGICAL SCIENCES↗

Videoshare

SAND2023-05132O Videoshare is an application that allows users to communicate in a variety of ways, including voice, video, and text, over a local network without having to use a central server or an internet connection. The software features: • Screen-sharing and connecting to external IP cameras. • Ability to hold group calls on computers running the same software and network. • Ability to connect to other computers running the same software. • Curating potential connections and manually adding IP addresses to available connections. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

McIlraith, Aiden↗

The use and abuse of cinnabar in Late Neolithic and Copper Age Iberia

Abstract In this study, total mercury (THg) was analyzed in archaeological human bone from 23 sites dating to between the Middle Neolithic and the Antiquity. A total of 370 individuals from individual or collective burials was sampled, mostly using cortical bone from the humerus. These individuals were recovered from over 50 different funerary structures ranging from tholoi, pits, caves, and hypogea. Although cinnabar (HgS) is a likely cause of mercury poisoning and toxicity for people exposed to this mineral from mining or use as a paint or pigment, not all sites investigated here had cinnabar associated with the burials or other excavated areas. We found unusual levels of THg in many of the sampled individuals that we assume were caused by exposure to cinnabar in life, and not by diagenetic processes or other exposures to mercury such as through diet, which would only cause negligible accumulation of THg in bone. Our data, based on the largest sampling ever undertaken on contamination of human bone through archaeological evidence, provide a baseline for additional research on cinnabar and its use in Prehistory. Moderate to high levels of THg in human bone are mainly associated with societies dating from the second half of the 4th to late 3rd millennia B.C. (Late Neolithic to Middle Chalcolithic) in southern Iberia. By the Late Chalcolithic and Early Bronze Age, the use of cinnabar decreased significantly and became minimal or absent. The use and abuse of cinnabar appears to have been pervasive throughout the above‐mentioned period and particularly between c. 2900–2300 B.C. This occurred in connection with the high symbolic and probably sacred value of the substance, which was sought after, traded, and extensively used in a variety of rituals and social practices.

Emslie, Steven D.↗

The value of protein structure classification information-Surveying the scientific literature

The Structural Classification of Proteins (SCOP) and Class, Architecture, Topology, Homology (CATH) databases have been valuable resources for protein structure classification for over 20 years. Development of SCOP (version 1) concluded in June 2009 with SCOP 1.75. The SCOPe (SCOP-extended) database offers continued development of the classic SCOP hierarchy, adding over 33,000 structures. We have attempted to assess the impact of these two decade old resources and guide future development. To this end, we surveyed recent articles to learn how structure classification data are used. Of 571 articles published in 2012-2013 that cite SCOP, 439 actually use data from the resource. We found that the type of use was fairly evenly distributed among four top categories: A) study protein structure or evolution (27% of articles), B) train and/or benchmark algorithms (28% of articles), C) augment non-SCOP datasets with SCOP classification (21% of articles), and D) examine the classification of one protein/a small set of proteins (22% of articles). Most articles described computational research, although 11% described purely experimental research, and a further 9% included both. We examined how CATH and SCOP were used in 158 articles that cited both databases: while some studies used only one dataset, the majority used data from both resources. Protein structure classification remains highly relevant for a diverse range of problems and settings.

59 BASIC BIOLOGICAL SCIENCES↗

Mapping use cases and dataset needs for benchmarking buildings data

A perennial challenge in buildings research is the lack of high-quality datasets that can be relied upon for a wide array of tasks, including model calibration and improving energy efficiency and load flexibility. Instrumenting a building for data collection is resource intensive, so it is important to be methodical in the approach and ensure that resulting data are flexible and useful for a broad range of analyses. This study aims to fill the gaps in characterizing potential use cases for buildings datasets and mapping them to dataset needs using a well-defined data infrastructure. Here, we have developed a systematic mapping strategy between buildings dataset needs and use cases to help streamline the processes of efficiently targeting datasets, designing building sensing systems, and determining buildings research use cases. We selected 14 prospective use cases and 11 refined buildings data categories for developing the preliminary dataset-needs-to-use-cases mapping matrix (‘DN-UC mapping matrix’) with generic ‘Tags’—a detailed sub-level of data categories extracted by justifying the needs of an aspect of the datasets to use cases. We present two example applications of the developed mapping matrix to demonstrate use of the mapping matrix and its effectiveness.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Lowering the barrier to access information-rich transient kinetic data for machine learning methods

Transient kinetic data contain a wealth of information about intrinsic features of a catalyst as well as the reaction mechanism. Currently, high volume transient data is underutilized, and data science methods could both increase the value of information that can be extracted from this data, integrate experimental with theoretical data sources, and accelerate the pace of catalyst technology advancement. Transient kinetic characterizations with simple probe molecules exhibiting reversible adsorption, irreversible adsorption and bulk-surface diffusion are presented as training components for similar experiments with more complex surface reactions. In conclusion, by increasing the availability and accessibility of transient kinetic data through details of its structure and acquisition, we aim to decrease the barrier for data scientists to apply machine learning methods to this valuable data source.

Catalysis↗