Renan Souza, Ph.D.

Abstract. Large Language Models (LLMs) and other foundation models are increasingly used as the core of AI agents. In agentic workflows, these agents plan tasks, interact with humans and peers, and influence scientific outcomes across federated and heterogeneous environments. However, agents can hallucinate or reason incorrectly, propagating errors when one agent's output becomes another's input. Thus, assuring that agents' actions are transparent, traceable, reproducible, and reliable is critical to assess hallucination risks and mitigate their workflow impacts. While provenance techniques have long supported these principles, existing methods fail to capture and relate agent-centric metadata such as prompts, responses, and decisions with the broader workflow context and downstream outcomes. In this paper, we introduce PROV-AGENT, a provenance model that extends W3C PROV and leverages the Model Context Protocol (MCP) and data observability to integrate agent interactions into end-to-end workflow provenance. Our contributions include: (1) a provenance model tailored for agentic workflows, (2) a near real-time, open-source system for capturing agentic provenance, and (3) a cross-facility evaluation spanning edge, cloud, and HPC environments, demonstrating support for critical provenance queries and agent reliability analysis.

Abstract. As Artificial Intelligence (AI) becomes more pervasive in our society, it is crucial to develop, deploy, and assess Responsible and Trustworthy AI (RTAI) models, i.e., those that consider not only accuracy but also other aspects, such as explainability, fairness, and energy efficiency. Workflow provenance data have historically enabled critical capabilities towards RTAI. Provenance data derivation paths contribute to responsible workflows through transparency in tracking artifacts and resource consumption. Provenance data are well-known for their trustworthiness, helping explainability, reproducibility, and accountability. However, there are complex challenges to achieving RTAI, which are further complicated by the heterogeneous infrastructure in the computing continuum (Edge-Cloud-HPC) used to develop and deploy models. As a result, a significant research and development gap remains between workflow provenance data management and RTAI. In this paper, we present a vision of the pivotal role of workflow provenance in supporting RTAI and discuss related challenges. We present a schematic view of the relationship between RTAI and provenance, and highlight open research directions.

Abstract. Modern large-scale scientific discovery requires multidisciplinary collaboration across diverse computing facilities, including High Performance Computing (HPC) machines and the Edge-to-Cloud continuum. Integrated data analysis plays a crucial role in scientific discovery, especially in the current AI era, by enabling Responsible AI development, FAIR, Reproducibility, and User Steering. However, the heterogeneous nature of science poses challenges such as dealing with multiple supporting tools, cross-facility environments, and efficient HPC execution. Building on data observability, adapter system design, and provenance, we propose MIDA: an approach for lightweight runtime Multi-workflow Integrated Data Analysis. MIDA defines data observability strategies and adaptability methods for various parallel systems and machine learning tools. With observability, it intercepts the dataflows in the background without requiring instrumentation while integrating domain, provenance, and telemetry data at runtime into a unified database ready for user steering queries. We conduct experiments showing end-to-end multi-workflow analysis integrating data from Dask and MLFlow in a real distributed deep learning use case for materials science that runs on multiple environments with up to 276 GPUs in parallel. We show near-zero overhead running up to 100,000 tasks on 1,680 CPU cores on the Summit supercomputer.

Abstract. Machine Learning (ML) has already fundamentally changed several businesses. More recently, it has also been profoundly impacting the computational science and engineering domains, like geoscience, climate science, and health science. In these domains, users need to perform comprehensive data analyses combining scientific data and ML models to provide for critical requirements, such as reproducibility, model explainability, and experiment data understanding. However, scientific ML is multidisciplinary, heterogeneous, and affected by the physical constraints of the domain, making such analyses even more challenging. In this work, we leverage workflow provenance techniques to build a holistic view to support the lifecycle of scientific ML. We contribute with (i) characterization of the lifecycle and taxonomy for data analyses; (ii) design principles to build this view, with a W3C PROV compliant data representation and a reference system architecture; and (iii) lessons learned after an evaluation in an Oil \& Gas case using an HPC cluster with 393 nodes and 946 GPUs. The experiments show that the principles enable queries that integrate domain semantics with ML models while keeping low overhead (<1\%), high scalability, and an order of magnitude of query acceleration under certain workloads against without our representation.

Abstract. Complex scientific experiments from various domains are typically modeled as workflows and executed on large-scale machines using a Parallel Workflow Management System (WMS). Since such executions usually last for hours or days, some WMSs provide user steering support, i.e., they allow users to run data analyses and, depending on the results, adapt the workflows at runtime. A challenge in the parallel execution control design is to manage workflow data for efficient executions while enabling user steering support. Data access for high scalability is typically transaction-oriented, while for data analysis, it is online analytical-oriented so that managing such hybrid workloads makes the challenge even harder. In this work, we present SchalaDB, an architecture with a set of design principles and techniques based on distributed in-memory data management for efficient workflow execution control and user steering. We propose a distributed data design for scalable workflow task scheduling and high availability driven by a parallel and distributed in-memory DBMS. To evaluate our proposal, we develop d-Chiron, a WMS designed according to SchalaDB's principles. We carry out an extensive experimental evaluation on an HPC cluster with up to 960 computing cores. Among other analyses, we show that even when running data analyses for user steering, SchalaDB's overhead is negligible for workloads composed of hundreds of concurrent tasks on shared data. Our results encourage workflow engine developers to follow a parallel and distributed data-oriented approach not only for scheduling and monitoring but also for user steering.

Abstract. Machine Learning (ML) has already fundamentally changed several businesses. More recently, it has also been profoundly impacting the computational science and engineering domains, like geoscience, climate science, and health science. In these domains, users need to perform comprehensive data analyses combining scientific data and ML models to provide for critical requirements, such as reproducibility, model explainability, and experiment data understanding. However, scientific ML is multidisciplinary, heterogeneous, and affected by the physical constraints of the domain, making such analyses even more challenging. In this work, we leverage workflow provenance techniques to build a holistic view to support the lifecycle of scientific ML. We contribute with (i) characterization of the lifecycle and taxonomy for data analyses; (ii) design principles to build this view, with a W3C PROV compliant data representation and a reference system architecture; and (iii) lessons learned after an evaluation in an Oil \& Gas case using an HPC cluster with 393 nodes and 946 GPUs. The experiments show that the principles enable queries that integrate domain semantics with ML models while keeping low overhead (<1\%), high scalability, and an order of magnitude of query acceleration under certain workloads against without our representation.

Abstract. In long-lasting scientific workflow executions in HPC machines, computational scientists (the users in this work) often need to fine-tune several workflow parameters. These tunings are done through user steering actions that may significantly improve performance (e.g., reduce execution time) or improve the overall results. However, in executions that last for weeks, users can lose track of what has been adapted if the tunings are not properly registered. In this work, we build on provenance data management to address the problem of tracking online parameter fine-tuning in dynamic workflows steered by users. We propose a lightweight solution to capture and manage provenance of the steering actions online with negligible overhead. The resulting provenance database relates tuning data with data for domain, dataflow provenance, execution, and performance, and is available for analysis at runtime. We show how users may get a detailed view of the execution, providing insights to determine when and how to tune. We discuss the applicability of our solution in different domains and validate its ability to allow for online capture and analyses of parameter fine-tunings in a real workflow in the Oil and Gas industry. In this experiment, the user could determine which tuned parameters influenced simulation accuracy and performance. The observed overhead for keeping track of user steering actions at runtime is less than 1\% of total execution time.

Abstract. Scientific workflows need to be iteratively, and often interactively, executed for large input datasets. Reducing data from input datasets is a powerful way to reduce overall execution time in such workflows. When this is accomplished online (i.e., without requiring the user to stop execution to reduce the data, and then resume), it can save much time. However, determining which subsets of the input data should be removed becomes a major problem. A related problem is to guarantee that the workflow system will maintain execution and data consistent with the reduction. Keeping track of how users interact with the workflow is essential for data provenance purposes. In this paper, we adopt the “human-in-the-loop” approach, which enables users to steer the running workflow and reduce subsets from datasets online. We propose an adaptive workflow monitoring approach that combines provenance data monitoring and computational steering to support users in analyzing the evolution of key parameters and determining the subset of data to remove. We extend a provenance data model to keep track of users’ interactions when they reduce data at runtime. In our experimental validation, we develop a test case from the oil and gas domain, using a 936-cores cluster. The results on this test case show that the approach yields reductions of 32\% of execution time and 14\% of the data processed.

Abstract. Large Language Models (LLMs) and other foundation models are increasingly used as the core of AI agents. In agentic workflows, these agents plan tasks, interact with humans and peers, and influence scientific outcomes across federated and heterogeneous environments. However, agents can hallucinate or reason incorrectly, propagating errors when one agent's output becomes another's input. Thus, assuring that agents' actions are transparent, traceable, reproducible, and reliable is critical to assess hallucination risks and mitigate their workflow impacts. While provenance techniques have long supported these principles, existing methods fail to capture and relate agent-centric metadata such as prompts, responses, and decisions with the broader workflow context and downstream outcomes. In this paper, we introduce PROV-AGENT, a provenance model that extends W3C PROV and leverages the Model Context Protocol (MCP) and data observability to integrate agent interactions into end-to-end workflow provenance. Our contributions include: (1) a provenance model tailored for agentic workflows, (2) a near real-time, open-source system for capturing agentic provenance, and (3) a cross-facility evaluation spanning edge, cloud, and HPC environments, demonstrating support for critical provenance queries and agent reliability analysis.

Abstract. Modern scientific discovery increasingly relies on workflows that process data across the Edge, Cloud, and High Performance Computing (HPC) continuum. Comprehensive and in-depth analyses of these data are critical for hypothesis validation, anomaly detection, reproducibility, and impactful findings. Although workflow provenance techniques support such analyses, at large scale, the provenance data become complex and difficult to analyze. Existing systems depend on custom scripts, structured queries, or static dashboards, limiting data interaction. In this work, we introduce an evaluation methodology, reference architecture, and open-source implementation that leverages interactive Large Language Model (LLM) agents for runtime data analysis. Our approach uses a lightweight, metadata-driven design that translates natural language into structured provenance queries. Evaluations across LLaMA, GPT, Gemini, and Claude, covering diverse query classes and a real-world chemistry workflow, show that modular design, prompt tuning, and Retrieval-Augmented Generation (RAG) enable accurate and insightful LLM agent responses beyond recorded provenance.

Abstract. As Artificial Intelligence (AI) becomes more pervasive in our society, it is crucial to develop, deploy, and assess Responsible and Trustworthy AI (RTAI) models, i.e., those that consider not only accuracy but also other aspects, such as explainability, fairness, and energy efficiency. Workflow provenance data have historically enabled critical capabilities towards RTAI. Provenance data derivation paths contribute to responsible workflows through transparency in tracking artifacts and resource consumption. Provenance data are well-known for their trustworthiness, helping explainability, reproducibility, and accountability. However, there are complex challenges to achieving RTAI, which are further complicated by the heterogeneous infrastructure in the computing continuum (Edge-Cloud-HPC) used to develop and deploy models. As a result, a significant research and development gap remains between workflow provenance data management and RTAI. In this paper, we present a vision of the pivotal role of workflow provenance in supporting RTAI and discuss related challenges. We present a schematic view of the relationship between RTAI and provenance, and highlight open research directions.

Abstract. Modern large-scale scientific discovery requires multidisciplinary collaboration across diverse computing facilities, including High Performance Computing (HPC) machines and the Edge-to-Cloud continuum. Integrated data analysis plays a crucial role in scientific discovery, especially in the current AI era, by enabling Responsible AI development, FAIR, Reproducibility, and User Steering. However, the heterogeneous nature of science poses challenges such as dealing with multiple supporting tools, cross-facility environments, and efficient HPC execution. Building on data observability, adapter system design, and provenance, we propose MIDA: an approach for lightweight runtime Multi-workflow Integrated Data Analysis. MIDA defines data observability strategies and adaptability methods for various parallel systems and machine learning tools. With observability, it intercepts the dataflows in the background without requiring instrumentation while integrating domain, provenance, and telemetry data at runtime into a unified database ready for user steering queries. We conduct experiments showing end-to-end multi-workflow analysis integrating data from Dask and MLFlow in a real distributed deep learning use case for materials science that runs on multiple environments with up to 276 GPUs in parallel. We show near-zero overhead running up to 100,000 tasks on 1,680 CPU cores on the Summit supercomputer.

Abstract. Machine Learning (ML) has become essential in several industries. In Computational Science and Engineering (CSE), the complexity of the ML lifecycle comes from the large variety of data, scientists' expertise, tools, and workflows. If data are not tracked properly during the lifecycle, it becomes unfeasible to recreate a ML model from scratch or to explain to stakeholders how it was created. The main limitation of provenance tracking solutions is that they cannot cope with provenance capture and integration of domain and ML data processed in the multiple workflows in the lifecycle while keeping the provenance capture overhead low. To handle this problem, in this paper we contribute with a detailed characterization of provenance data in the ML lifecycle in CSE; a new provenance data representation, called PROV-ML, built on top of W3C PROV and ML Schema; and extensions to a system that tracks provenance from multiple workflows to address the characteristics of ML and CSE, and to allow for provenance queries with a standard vocabulary. We show a practical use in a real case in the Oil and Gas industry, along with its evaluation using 48 GPUs in parallel.

Abstract. Computational Science and Engineering (CSE) projects are typically developed by multidisciplinary teams. Despite being part of the same project, each team manages its own workflows, using specific execution environments and data processingtools. Analyzing the data processed by all workflows globally is a core task in a CSE project. However, this analysis is hard because the data generated by these workflows are not integrated. In addition, since these workflows may take a long time to execute, data analysis needs to be done at runtime to reduce cost and time of the CSE project. A typical solution in scientific data analysis is to capture and relate the data in a provenance database while the workflows run, thus allowing for data analysisat runtime. However, the main problem is that such data capture competes with the running workflows, adding significant overhead to their execution. To mitigate this problem, we introduce in this paper a system called ProvLake, which adopts design principles for providing efficientdistributed data capture from the workflows. While capturing the data, ProvLake logically integrates and ingests them into a provenance database ready for analyses at runtime. We validated ProvLake ina real use case in the O&G industry encompassing four workflows that process 5TB datasets for a deep learning classifier. Compared with Komadu, the closest solution that meets our goals, our approach enables runtime multiworkflow data analysis with much smaller overhead, such as 0.1\%.