Search NASA⌕ Search

SEARCH · Search NASA

Results for “AI”

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

SU-F-19A-09: Propagation of Organ at Risk Contours for High Dose Rate Brachytherapy Planning for Cervical Cancer: A Deformable Image Registration Comparison

Purpose: To compare the performance of two deformable image registration (DIR) algorithms for contour propagation and to evaluate the accuracy of DIR for use with high dose rate (HDR) brachytherapy planning for cervical cancer. Methods: Five patients undergoing HDR ring and tandem brachytherapy were included in this retrospective study. All patients underwent CT simulation and replanning prior to each fraction (3–5 fractions total). CT-to-CT DIR was performed using two commercially available software platforms: SmartAdapt, Varian Medical Systems (Demons) and Velocity AI, Velocity Medical Solutions (B-spline). Fraction 1 contours were deformed and propagated to each subsequent image set and compared to contours manually drawn by an expert clinician. Dice similarity coefficients (DSC), defined as, DSC(A,B)=2(AandB)/(A+B) were calculated to quantify spatial overlap between manual (A) and deformed (B) contours. Additionally, clinician-assigned visual scores were used to describe and compare the performance of each DIR method and ultimately evaluate which was more clinically acceptable. Scoring was based on a 1–5 scale—with 1 meaning, “clinically acceptable with no contour changes” and 5 meaning, “clinically unacceptable”. Results: Statistically significant differences were not observed between the two DIR algorithms. The average DSC for the bladder, rectum and rectosigmoid were 0.82±0.08, 0.67±0.13 and 0.48±0.18, respectively. The poorest contour agreement was observed for the rectosigmoid due to limited soft tissue contrast and drastic anatomical changes, i.e., organ shape/filling. Two clinicians gave nearly equivalent average scores of 2.75±0.91 for SmartAdapt and 2.75±0.94 for Velocity AI—indicating that for a majority of the cases, more than one of the three contours evaluated required major modifications. Conclusion: Limitations of both DIR algorithms resulted in inaccuracies in contour propagation in the pelvic region, thus hampering the clinical utility of this technology. Further work is required to optimize these algorithms and take advantage of the potential of DIR for HDR brachytherapy planning.

60 APPLIED LIFE SCIENCES↗

SU-C-207B-07: Deep Convolutional Neural Network Image Matching for Ultrasound Guidance in Radiotherapy

Purpose: Robust matching of ultrasound images is a challenging problem as images of the same anatomy often present non-trivial differences. This poses an obstacle for ultrasound guidance in radiotherapy. Thus our objective is to overcome this obstacle by designing and evaluating an image blocks matching framework based on a two channel deep convolutional neural network. Methods: We extend to 3D an algorithmic structure previously introduced for 2D image feature learning [1]. To obtain the similarity between two 3D image blocks A and B, the 3D image blocks are divided into 2D patches Ai and Bi. The similarity is then calculated as the average similarity score of Ai and Bi. The neural network was then trained with public non-medical image pairs, and subsequently evaluated on ultrasound image blocks for the following scenarios: (S1) same image blocks with/without shifts (A and A-shift-x); (S2) non-related random block pairs; (S3) ground truth registration matched pairs of different ultrasound images with/without shifts (A-i and A-reg-i-shift-x). Results: For S1 the similarity scores of A and A-shift-x were 32.63, 18.38, 12.95, 9.23, 2.15 and 0.43 for x=ranging from 0 mm to 10 mm in 2 mm increments. For S2 the average similarity score for non-related block pairs was −1.15. For S3 the average similarity score of ground truth registration matched blocks A-i and A-reg-i-shift-0 (1≤i≤5) was 12.37. After translating A-reg-i-shift-0 by 0 mm, 2 mm, 4 mm, 6 mm, 8 mm, and 10 mm, the average similarity scores of A-i and A-reg-i-shift-x were 11.04, 8.42, 4.56, 2.27, and 0.29 respectively. Conclusion: The proposed method correctly assigns highest similarity to corresponding 3D ultrasound image blocks despite differences in image content and thus can form the basis for ultrasound image registration and tracking.[1] Zagoruyko, Komodakis, “Learning to compare image patches via convolutional neural networks', IEEE CVPR 2015,pp.4353–4361.

60 APPLIED LIFE SCIENCES↗

Coronary artery analysis: Computer-assisted selection of best-quality segments in multiple-phase coronary CT angiography

Purpose: The authors are developing an automated method to identify the best-quality coronary arterial segment from multiple-phase coronary CT angiography (cCTA) acquisitions, which may be used by either interpreting physicians or computer-aided detection systems to optimally and efficiently utilize the diagnostic information available in multiple-phase cCTA for the detection of coronary artery disease. Methods: After initialization with a manually identified seed point, each coronary artery tree is automatically extracted from multiple cCTA phases using our multiscale coronary artery response enhancement and 3D rolling balloon region growing vessel segmentation and tracking method. The coronary artery trees from multiple phases are then aligned by a global registration using an affine transformation with quadratic terms and nonlinear simplex optimization, followed by a local registration using a cubic B-spline method with fast localized optimization. The corresponding coronary arteries among the available phases are identified using a recursive coronary segment matching method. Each of the identified vessel segments is transformed by the curved planar reformation (CPR) method. Four features are extracted from each corresponding segment as quality indicators in the original computed tomography volume and the straightened CPR volume, and each quality indicator is used as a voting classifier for the arterial segment. A weighted voting ensemble (WVE) classifier is designed to combine the votes of the four voting classifiers for each corresponding segment. The segment with the highest WVE vote is then selected as the best-quality segment. In this study, the training and test sets consisted of 6 and 20 cCTA cases, respectively, each with 6 phases, containing a total of 156 cCTA volumes and 312 coronary artery trees. An observer preference study was also conducted with one expert cardiothoracic radiologist and four nonradiologist readers to visually rank vessel segment quality. The performance of our automated method was evaluated by comparing the automatically identified best-quality segments identified by the computer to those selected by the observers. Results: For the 20 test cases, 254 groups of corresponding vessel segments were identified after multiple phase registration and recursive matching. The AI-BQ segments agreed with the radiologist’s top 2 ranked segments in 78.3% of the 254 groups (Cohen’s kappa 0.60), and with the 4 nonradiologist observers in 76.8%, 84.3%, 83.9%, and 85.8% of the 254 groups. In addition, 89.4% of the AI-BQ segments agreed with at least two observers’ top 2 rankings, and 96.5% agreed with at least one observer’s top 2 rankings. In comparison, agreement between the four observers’ top ranked segment and the radiologist’s top 2 ranked segments were 79.9%, 80.7%, 82.3%, and 76.8%, respectively, with kappa values ranging from 0.56 to 0.68. Conclusions: The performance of our automated method for selecting the best-quality coronary segments from a multiple-phase cCTA acquisition was comparable to the selection made by human observers. This study demonstrates the potential usefulness of the automated method in clinical practice, enabling interpreting physicians to fully utilize the best available information in cCTA for diagnosis of coronary disease, without requiring manual search through the multiple phases and minimizing the variability in image phase selection for evaluation of coronary artery segments across the diversity of human readers with variations in expertise.

61 RADIATION PROTECTION AND DOSIMETRY↗

Explainable and trustworthy artificial intelligence for correctable modeling in chemical sciences

Data science has primarily focused on big data, but for many physics, chemistry, and engineering applications, data are often small, correlated and, thus, low dimensional, and sourced from both computations and experiments with various levels of noise. Typical statistics and machine learning methods do not work for these cases. Expert knowledge is essential, but a systematic framework for incorporating it into physics-based models under uncertainty is lacking. Here, we develop a mathematical and computational framework for probabilistic artificial intelligence (AI)–based predictive modeling combining data, expert knowledge, multiscale models, and information theory through uncertainty quantification and probabilistic graphical models (PGMs). We apply PGMs to chemistry specifically and develop predictive guarantees for PGMs generally. Our proposed framework, combining AI and uncertainty quantification, provides explainable results leading to correctable and, eventually, trustworthy models. The proposed framework is demonstrated on a microkinetic model of the oxygen reduction reaction.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Attention to quantum complexity

The imminent era of error-corrected quantum computing demands robust methods to characterize quantum state complexity from limited, noisy measurements. We introduce the Quantum Attention Network (QuAN), a classical artificial intelligence (AI) framework leveraging attention mechanisms tailored for learning quantum complexity. Inspired by large language models, QuAN treats measurement snapshots as tokens while respecting permutation invariance. Combined with our parameter-efficient miniset self-attention block, this enables QuAN to access high-order moments of bit-string distributions and preferentially attend to less noisy snapshots. We test QuAN across three quantum simulation settings: driven hard-core Bose-Hubbard model, random quantum circuits, and toric code under coherent and incoherent noise. QuAN directly learns entanglement and state complexity growth from experimental computational basis measurements, including complexity growth in random circuits from noisy data. In regimes inaccessible to existing theory, QuAN unveils the complete phase diagram for noisy toric code data as a function of both noise types, highlighting AI’s transformative potential for assisting quantum hardware.

Kim, Hyejin [Cornell Univ., Ithaca, NY (United Sta↗

AIIO: Using Artificial Intelligence for Job-Level and Automatic I/O Performance Bottleneck Diagnosis

Manually diagnosing the I/O performance bottleneck for a single application (hereinafter referred to as the "job level'') is a tedious and error-prone procedure requiring domain scientists to have deep knowledge of complex storage systems. However, existing automatic methods for I/O performance bottleneck diagnosis have one major issue: the granularity of the analysis is at the platform or group level and the diagnosis results cannot be applied to the individual application. To address this issue, we designed and developed a method named "Artificial Intelligence for I/O"(AIIO), which uses AI and its interpretation technology to diagnose I/O performance bottlenecks at the job level automatically. By considering the sparsity of I/O log files, employing multiple AI models for performance prediction, merging diagnosis results across multiple models, and generalizing its performance prediction and diagnosis functions, AIIO can accurately and robustly identify the bottleneck of an even unseen application. Experimental results show that real and unseen applications can use the diagnosis results from AIIO to improve their I/O performance by at most 146 times.

Dong, Bin↗

Evaluation of OpenAI Codex for HPC Parallel Programming Models Kernel Generation

We evaluate AI-assisted generative capabilities on fundamental numerical kernels in high-performance computing (HPC), including AXPY, GEMV, GEMM, SpMV, Jacobi Stencil, and CG. We test the generated kernel codes for a variety of language-supported programming models, including (1) C++ (e.g., OpenMP [including offload], OpenACC, Kokkos, SyCL, CUDA, and HIP), (2) Fortran (e.g., OpenMP [including offload] and OpenACC), (3) Python (e.g., numpy, Numba, cuPy, and pyCUDA), and (4) Julia (e.g., Threads, CUDA.jl, AMDGPU.jl, and KernelAbstractions.jl). We use the GitHub Copilot capabilities powered by the GPT-based OpenAI Codex available in Visual Studio Code as of April 2023 to generate a vast amount of implementations given simple + + prompt variants. To quantify and compare the results, we propose a proficiency metric around the initial 10 suggestions given for each prompt. Results suggest that the OpenAI Codex outputs for C++ correlate with the adoption and maturity of programming models. For example, OpenMP and CUDA score really high, whereas HIP is still lacking. We found that prompts from either a targeted language such as Fortran or the more general purpose Python can benefit from adding code keywords, while Julia prompts perform acceptably well for its mature programming models (e.g., Threads and CUDA.jl). We expect for these benchmarks to provide a point of reference for each programming model's community. Overall, understanding the convergence of large language models, AI, and HPC is crucial due to its rapidly evolving nature and how it is redefining human-computer interactions.

Godoy, William↗

Tencoder: tensor-product encoder-decoder architecture for predicting solutions of PDEs with variable boundary data

It is widely hoped that artificial intelligence will boost data-driven surrogate models in science and engineering. However, fundamental spatial aspects of AI surrogate models remain under-studied. We investigate the ability of neural-network surrogate models to predict solutions to PDEs under variable boundary values. We do not wish to retrain the model when the boundary values change but to make them inputs to the model and infer the solution of the PDE under those boundary conditions. Such a capability is essential to making AI-based surrogate models practically useful. While simple feedforward networks are used for one-dimensional (1D) Poisson equation, an encoder-decoder architecture with a tensor-product layer is developed for the two-dimensional Poisson equation posed on a rectangular domain. We show that it is indeed possible to infer solutions to PDEs from variable boundary data using neural networks in this relatively simple setting, and point to future directions.

Kashi, Aditya↗

Topological Interpretability for Deep Learning

With the growing adoption of AI-based systems across everyday life, the need to understand their decision-making mechanisms is correspondingly increasing. The level at which we can trust the statistical inferences made from AI-based decision systems is an increasing concern, especially in high-risk systems such as criminal justice or medical diagnosis, where incorrect inferences may have tragic consequences. Despite their successes in providing solutions to problems involving real-world data, deep learning (DL) models cannot quantify the certainty of their predictions. These models are frequently quite confident, even when their solutions are incorrect. This work presents a method to infer prominent features in two DL classification models trained on clinical and non-clinical text by employing techniques from topological and geometric data analysis. We create a graph of a model's feature space and cluster the inputs into the graph's vertices by the similarity of features and prediction statistics. We then extract subgraphs demonstrating high-predictive accuracy for a given label. These subgraphs contain a wealth of information about features that the DL model has recognized as relevant to its decisions. We infer these features for a given label using a distance metric between probability measures, and demonstrate the stability of our method compared to the LIME and SHAP interpretability methods. This work establishes that we may gain insights into the decision mechanism of a DL model. This method allows us to ascertain if the model is making its decisions based on information germane to the problem or identifies extraneous patterns within the data.

Spannaus, Adam↗

High-Throughput Computing: Case Study of Medical Image Processing Applications

HPC is designed for large-scale simulations using monolithic codes of tightly coupled processes highly optimized to deliver decreased time to solution. Medical image processing is not a traditional field of HPC. Similar to AI applications, medical image processing parses large datasets, typically multiple times, to support a variety of studies for classification, diagnosis or monitoring purposes. The convergence of AI, HPC and Big Data encouraged more fields using image processing to transition to HPC. However, not all applications benefit from the same optimizations. In this paper we focus on high throughput medical image processing applications that analyze a huge dataset of small MRI images and that require HPC systems to decrease the time of parsing the entire dataset and not individual MRIs. We show in this research the performance of running SLANT, an image processing application for a whole brain segmentation, on large-scale systems and highlight performance limitations. We present optimizations prioritizing throughput that exhibit a 3.5x speed-up on the Summit Supercomputer that can be used as a baseline for building a high-throughput execution framework for other HPC systems.

Predescu, Maria↗

I/O in Machine Learning Applications on HPC Systems: A 360-degree Survey

Growing interest in Artificial Intelligence (AI) has resulted in a surge in demand for faster methods of Machine Learning (ML) model training and inference. This demand for speed has prompted the use of high performance computing (HPC) systems that excel in managing distributed workloads. Because data is the main fuel for AI applications, the performance of the storage and I/O subsystem of HPC systems is critical. In the past, HPC applications accessed large portions of data written by simulations or experiments or ingested data for visualizations or analysis tasks. ML workloads perform small reads spread across a large number of random files. This shift of I/O access patterns poses several challenges to modern parallel storage systems. In this paper, we survey I/O in ML applications on HPC systems, and target literature within a 6-year time window from 2019 to 2024. We define the scope of the survey, provide an overview of the common phases of ML, review available profilers and benchmarks, examine the I/O patterns encountered during offline data preparation, training, and inference, and explore I/O optimizations utilized in modern ML frameworks and proposed in recent literature. Lastly, we seek to expose research gaps that could spawn further R&D.

97 MATHEMATICS AND COMPUTING↗

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)↗

Data Science in Chemical Engineering: Applications to Molecular Science

Chemical engineering is being rapidly transformed by the tools of data science. On the horizon, artificial intelligence (AI) applications will impact a huge swath of our work, ranging from the discovery and design of new molecules to operations and manufacturing and many areas in between. Early adoption of data science, machine learning, and early examples of AI in chemical engineering has been rich with examples of molecular data science—the application tools for molecular discovery and property optimization at the atomic scale. Here, we summarize key advances in this nascent subfield while introducing molecular data science for a broad chemical engineering readership. We introduce the field through the concept of a molecular data science life cycle and discuss relevant aspects of five distinct phases of this process: creation of curated data sets, molecular representations, data-driven property prediction, generation of new molecules, and feasibility and synthesizability considerations.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

bnl/pub-Maffettone_2020_08

The application of the XCA package as first demonstrated in aXiv:2008.00283. ABSTRACT: The discovery of new structural and functional materials is driven by phase identification, often using X-ray diffraction (XRD). Automation has accelerated the rate of XRD measurements, greatly outpacing XRD analysis techniques that remain manual, time consuming, error prone, and impossible to scale. With the advent of autonomous robotic scientists or self-driving labs, contemporary techniques prohibit the integration of XRD. Here, we describe a computer program for the autonomous characterization of XRD data, driven by artificial intelligence (AI), for the discovery of new materials. Starting from structural databases, we train an ensemble model using a physically accurate synthetic dataset, which output probabilistic classifications --- rather than absolutes --- to overcome the overconfidence in traditional neural networks. This AI agent behaves as a companion to the researcher, improving accuracy and offering unprecedented time savings, and is demonstrated on a diverse set of organic and inorganic materials challenges. This innovation is directly applicable to inverse design approaches, robotic discovery systems, and can be immediately considered for other forms of characterization such as spectroscopy and the pair distribution function.

Maffettone, PhillipM [Brookhaven National Lab. (BN↗

OGhidra

This is an AI driven Binary Analysis tool. It uses locally hosted Agentic AI's to automatically reverse engineer binaries to find malware and vulnerabilities.

Wang, Enoch↗

AstraAI v1

AstraAI is an open-source, structure-aware AI coding agent designed for large scientific and DOE-HPC codebases such as AMReX-based applications. Unlike general-purpose coding assistants, AstraAI combines retrieval-augmented generation (RAG) with compiler-level Abstract Syntax Tree (AST) analysis to perform precise, scope-constrained code modifications. It identifies exact function spans, enforces locality of edits, and maintains cross-file invariants, enabling deterministic and build-safe transformations in complex C++/GPU environments. AstraAI is intended for developers working on large, evolving HPC frameworks where correctness, reproducibility, and structural integrity are critical. Typical use cases include modifying physics kernels, updating GPU device lambdas, and performing multi-file refactors without breaking compilation or runtime semantics. Compared to conventional LLM-based coding agents - even those with repository access - AstraAI provides structural guarantees rather than free-form text patches. It minimizes unintended diffs, prevents scope drift, preserves formatting and build stability, and reduces structural hallucinations. By integrating compiler tooling directly into the generation loop, AstraAI transforms AI-assisted coding from probabilistic text editing into deterministic, structure-preserving program transformation suitable for mission-critical scientific software.

Natarajan, Mahesh [Lawrence Berkeley National Labo↗

datasight [SWR-26-045]

This software is an AI-powered data exploration with natural language. datasight connects an AI agent to your database and provides a web UI where you can ask questions in natural language. The agent writes SQL, runs queries, and generates interactive Plotly visualizations. Supports DuckDB, PostgreSQL, SQLite, and Flight SQL databases. Also queries local CSV and Parquet files directly — no database setup required. Supports Anthropic Claude (default), GitHub Models (open source), and Ollama (local) as LLM backends.

Thom, Daniel [National Laboratory of the Rockies (↗

matsim-agents v1.0

matsim-agents is a multi-agent AI framework for atomistic materials simulation and discovery. It orchestrates large language models (LLMs), machine-learned interatomic potentials (MLIPs), and DFT codes into a single agentic loop running on laptops and DOE leadership-class supercomputers. MULTI-AGENT ORCHESTRATION A LangGraph state machine with three nodes: a Planner that converts a natural-language research objective into structured tasks; an Executor that dispatches atomistic tools and loops until the queue is empty; and an Analyst that summarizes results into a human-readable report. State is checkpointed after every step and human-in-the-loop gates can be inserted at any edge. HYPOTHESIS-DRIVEN DISCOVERY CHAT An interactive REPL (matsim-agents chat) that couples LLM dialogue with atomistic simulation. Chemical formulas are automatically detected in conversation turns and trigger a full crystal-phase exploration: structure generation → relaxation → stability scoring → result injection back into the conversation, creating a closed hypothesis-refinement loop. CRYSTAL PHASE ENUMERATION Given a composition, the phase explorer enumerates prototypes by stoichiometry: elemental (fcc/bcc/hcp/sc/diamond), binary 1:1 (rocksalt/CsCl/zincblende/ wurtzite/fluorite/rutile), ternary 1:1:3 (cubic perovskite), ternary 1:2:4 (perovskite + spinel), quaternary 1:1:2:6 (Fm-3m double perovskite). 2-D prototypes (graphene, h-BN, MoS2 2H/1T) and multilayer stacking are also supported via --include-2d and --num-layers. SUPERCELL GENERATION AND SITE DECORATION Auto-tiling to a minimum atom count (--min-atoms), explicit NxNxN tiling (--supercell), symmetry-distinct site decorations (--n-orderings), and isotropic lattice-scale sweeps (--lattice-scales) for volume bracketing. MLFF RELAXATION AND STABILITY SCORING HydraGNN (multi-headed GNN) drives structure relaxation via ASE with FIRE, BFGS, or BFGSLineSearch. Stability output: delta-E/atom ranking across phases and a max-residual-force dynamical-stability proxy. Other MLIPs (MACE, NequIP, Orb) can be plugged in through the same interface. DFT BACKENDS Quantum ESPRESSO pw.x and VASP 6.6 are first-class labellers. Both have validated GPU builds and SLURM/PBS launchers for three DOE platforms: Frontier (AMD MI250X, ROCm), Aurora (Intel PVC, oneAPI), Perlmutter (NVIDIA A100, CUDA). QE produces ~100 binaries (pw.x, ph.x, epw.x, ...). VASP supports scf, relax, vc-relax, and vc-relax-shape run types. ACTIVE-LEARNING LOOP matsim-agents al run CONFIG.yaml drives an iterative HydraGNN-DFT loop: MD generates candidates → ensemble/MC-dropout uncertainty selects the most informative → DFT labels them in parallel inside one allocation → dataset grows → HydraGNN retrains → repeat. DFT backend is a single YAML toggle (dft.backend: vasp | qe). LLM-generated seed structures are supported (no curated POSCAR library needed). Config uses ${VAR}, ${VAR:-default}, ${VAR:?msg} shell-style substitution for cross-user/cross-site portability. LLM BACKENDS Ollama (local, default), vLLM (HPC multi-GPU serving), OpenAI, Anthropic, HuggingFace Transformers+Accelerate. Selected at runtime via flag or env var with no code changes. HPC PORTABILITY Same Python entry points run on Frontier (ROCm 7.2), Aurora (oneAPI), and Perlmutter (CUDA 12). DFT and ML stacks are never co-loaded in the same shell; they couple through the scheduler and filesystem. Advanced multi-node launchers (serve, discovery-chat, single-relaxation, active-learning, QE warm-start) are provided for all three platforms. CODABENCH COMPETITION BUNDLE A self-contained benchmark: 159 atomistic test structures across 11 material classes, 5 tasks (formation energy, forces, ML relaxation, AI-DFT relaxation, phase stability ranking), public/private leaderboard split (30/70), and four ready-to-run baselines: MACE-MP-0, HydraGNN, UMA, AllScAIP.

Lupo Pasini, Massimiliano [Oak Ridge National Labo↗