Publications

Flowcept Papers

Towards Lightweight Data Integration using Multi-workflow Provenance and Data Observability

R. Souza, T. J. Skluzacek, S. R. Wilkinson, M. Ziatdinov, and R. Ferreira da Silva. IEEE International Conference on e-Science, Limassol, Cyprus, 2023.

Introduces Flowcept’s lightweight runtime provenance and data observability architecture and shows minimal-intrusion capture across heterogeneous workflows.

Links: doi | pdf

PROV-AGENT: Unified Provenance for Tracking AI Agent Interactions in Agentic Workflows

R. Souza, A. Gueroudji, S. DeWitt, D. Rosendo, T. Ghosal, R. Ross, P. Balaprakash, and R. Ferreira da Silva. IEEE International Conference on e-Science, Chicago, USA, 2025.

Defines agentic provenance and a unified provenance model and tooling to capture, link, and query AI-agent interactions within agentic workflows.

Links: doi | pdf | html

Workflow Provenance in the Computing Continuum for Responsible, Trustworthy, and Energy-Efficient AI

R. Souza, S. Caino-Lores, M. Coletti, T. J. Skluzacek, A. Costan, F. Suter, M. Mattoso, and R. Ferreira da Silva. IEEE International Conference on e-Science, Osaka, Japan, 2024.

Explains how end-to-end provenance across edge, cloud, and HPC supports responsible, trustworthy, and energy-aware AI workflows.

Links: doi | pdf

LLM Agents for Interactive Workflow Provenance: Reference Architecture and Evaluation Methodology

R. Souza, T. Poteet, B. Etz, D. Rosendo, A. Gueroudji, W. Shin, P. Balaprakash, and R. Ferreira da Silva. Workflows in Support of Large-Scale Science (WORKS), co-located with SC, St. Louis, USA, 2025.

Presents a reference architecture and evaluation method for LLM agents that query and act on large-scale provenance databases.

Links: doi | pdf | html

Papers That Used Flowcept

Toward a Persistent Event-Streaming System for High-Performance Computing Applications

M. Dorier, A. Gueroudji, V. Hayot-Sasson, H. Nguyen, S. Ockerman, R. Souza, T. Bicer, H. Pan, P. Carns, K. Chard, and others. Frontiers in High Performance Computing, 2025.

Demonstrates Flowcept generating high-volume provenance that is persistently streamed with Mofka for HPC applications.

Links: doi | pdf | html

AI Agents for Enabling Autonomous Experiments at ORNL’s HPC and Manufacturing User Facilities

D. Rosendo, S. DeWitt, R. Souza, P. Austria, T. Ghosal, M. McDonnell, R. Miller, T. Skluzacek, J. Haley, B. Turcksin, and others. Extreme-Scale Experiment-in-the-Loop Computing (XLOOP), co-located with SC, 2025.

Leverages Flowcept’s agentic provenance to coordinate multi-agent experiments and connect agents with HPC simulations through a shared provenance stream.

Links: doi | pdf | html

BibTeX

@inproceedings{souza2023towards,
  title={Towards Lightweight Data Integration using Multi-workflow Provenance and Data Observability},
  author={Souza, Renan and Skluzacek, Tyler J and Wilkinson, Sean R and Ziatdinov, Maxim and da Silva, Rafael Ferreira},
  booktitle={IEEE International Conference on e-Science},
  doi={10.1109/e-Science58273.2023.10254822},
  url={https://doi.org/10.1109/e-Science58273.2023.10254822},
  pdf={https://arxiv.org/pdf/2308.09004.pdf},
  year={2023}
}

@inproceedings{souza_prov_agent_2025,
  author={Renan Souza and Amal Gueroudji and Stephen DeWitt and Daniel Rosendo and Tirthankar Ghosal and Robert Ross and Prasanna Balaprakash and Rafael Ferreira da Silva},
  title={PROV-AGENT: Unified Provenance for Tracking {AI} Agent Interactions in Agentic Workflows},
  booktitle={IEEE International Conference on e-Science},
  year={2025},
  doi={10.1109/eScience65000.2025.00093},
  pdf={https://arxiv.org/pdf/2508.02866}
}

@inproceedings{souza_rtai_2024,
  author={Renan Souza and Silvina Caino-Lores and Mark Coletti and Tyler J. Skluzacek and Alexandru Costan and Frederic Suter and Marta Mattoso and Rafael Ferreira da Silva},
  title={Workflow Provenance in the Computing Continuum for Responsible, Trustworthy, and Energy-Efficient {AI}},
  booktitle={IEEE International Conference on e-Science},
  year={2024},
  doi={10.1109/e-Science62913.2024.10678731},
  pdf={https://hal.science/hal-04902079v1/document}
}

@inproceedings{souza_llm_agents_works_sc25,
  title={{LLM} Agents for Interactive Workflow Provenance: Reference Architecture and Evaluation Methodology},
  author={Souza, Renan and Poteet, Timothy and Etz, Brian and Rosendo, Daniel and Gueroudji, Amal and others},
  booktitle={Workflows in Support of Large-Scale Science ({WORKS}) co-located with the {ACM}/{IEEE} International Conference for High Performance Computing, Networking, Storage, and Analysis ({SC})},
  year={2025},
  doi={10.1145/3731599.3767582}
}

@article{dorier2025toward,
  author={Dorier, Matthieu and Gueroudji, Amal and Hayot-Sasson, Valerie and Nguyen, Hai and Ockerman, Seth and Souza, Renan and Bicer, Tekin and Pan, Haochen and Carns, Philip and Chard, Kyle and others},
  doi={10.3389/fhpcp.2025.1638203},
  journal={Frontiers in High Performance Computing},
  title={Toward a Persistent Event-Streaming System for High-Performance Computing Applications},
  volume={3},
  year={2025}
}

@inproceedings{rosendo2025ai,
  author={Rosendo, Daniel and DeWitt, Stephen and Souza, Renan and Austria, Phillipe and Ghosal, Tirthankar and McDonnell, Marshall and Miller, Ross and Skluzacek, Tyler J and Haley, James and Turcksin, Bruno and others},
  booktitle={Extreme-Scale Experiment-in-the-Loop Computing ({XLOOP}) co-located with the {ACM}/{IEEE} International Conference for High Performance Computing, Networking, Storage, and Analysis ({SC})},
  title={AI Agents for Enabling Autonomous Experiments at ORNL's HPC and Manufacturing User Facilities},
  year={2025},
  doi={10.1145/3731599.3767592}
}