PROV-AGENT: Unified Provenance for Tracking AI Agent Interactions in Agentic Workflows
The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“By modeling AI agents' specific processes and data, such as their prompts, invocations, and outputs, as well as their interaction with general computing system processes and data structures, provenance graphs can accurately represent the history of heterogeneous multi-agent computing systems.”
From Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents (2025) · cites this paper as Souza et al., 2025
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Retrieval-Augmented Generation for Large Language Models: A Survey
Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Wang, M., & Wang, H. (2023) · arXiv · doi:10.48550/arxiv.2312.10997 · Cited by 876 · cited 1×
“MCP defines core agentic AI development concepts, including tools, prompts, resources, context management, and agent–client architecture that can communicate with external sources, such as knowledge bases or web pages, for Retrieval-Augmented Generation (RAG) [15] to dynamically augment prompts.”
Agentic AI: Autonomous intelligence for complex goals–a comprehensive survey
Acharya, D. B., Kuppan, K., & Divya, B. (2025) · IEEE Access · doi:10.1109/access.2025.3532853 · Cited by 717
Creating Large Language Model Applications Utilizing LangChain: A Primer on Developing LLM Apps Fast
Topsakal, O., & Akinci, T. C. (2023) · International Conference on Applied Engineering and Natural Sciences · doi:10.59287/icaens.1127 · Cited by 331 · cited 1×
“For instance, LangChain [10], [11], Au-toGen [12], LangGraph [13], Academy [3], and CrewAI [14] support multi-agent systems that interact through prompt exchanges, calls to foundation models typically hosted by AI service providers in the cloud (e.g., OpenAI, SambaNova), and shared context.”
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
Wu, Q., Bansal, G., Zhang, J., Wu, Y., Li, B., Zhu, E., Jiang, L., Zhang, X., Zhang, S., Liu, J., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.08155 · Cited by 193
AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2025) · SuperIntelligence - Robotics - Safety & Alignment · doi:10.70777/si.v2i3.15161 · Cited by 186
Wang, J., & Duan, Z. (2024) · arXiv · doi:10.48550/arxiv.2412.03801 · Cited by 8
Research works printed but not linked: 14
- Fettke, 2025, LLM, LAM, LxM Agent: From Talking to Acting Machines: Insights from the Perspective of Conceptual Modeling, Enterprise Modelling and Information Systems Architectures (EMISAJ), 20
- 10.1016/j.future.2025.107974 · DOI
- Gu, Agent smith: a single image can jailbreak one million multimodal llm agents exponentially fast
- 10.1109/e-Science62913.2024.10678731 · DOI
- Groth, 2013, W3C PROV: an overview of the prov family of documents
- Auffarth, 2023, Generative AI with LangChain: Build large language model (LLM) apps with Python, ChatGPT, and other LLMs
- 10.1109/MIS.2025.3544940 · DOI · Paper page
- 10.1109/e-Science58273.2023.10254822 · DOI
- 10.2172/2474744 · doi:10.2172/2474744
- 10.1007/978-3-319-98379-0_2 · DOI
- 10.1002/cpe.6544 · DOI
- 10.1109/eScience.2017.16 · DOI
- 10.1109/eScience.2019.00047 · DOI
- 10.1007/s00170-021-07682-3 · DOI · Paper page
Cited by
Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents
de Witt, C. S., Krawiecka, K., Krawczuk, I., Hagag, B., Anderson, W. L., Belcak, P., Bucknall, B., Cai, X., Chopra, A., Cohen, D., et al. (2025) · arXiv · doi:10.48550/arxiv.2505.02077 · Cited by 108
Metadata
- Authors
- Souza, R., Gueroudji, A., DeWitt, S., Rosendo, D., Ghosal, T., Ross, R., Balaprakash, P., & Da Silva, R. F.
- Affiliations
- Oak Ridge National Lab,National Center for Computational Sciences,Oak Ridge,TN,USA
- Argonne National Laboratory,Mathematics and Computer Science Division,Lemont,IL,USA
- Oak Ridge National Lab,Computational Sciences and Engineering Division,Oak Ridge,TN,USA
- Oak Ridge National Lab,Computer Science and Mathematics Division,Oak Ridge,TN,USA
- Venue
- 2025 IEEE International Conference on eScience (eScience)
- Publisher
- IEEE
- Published
- 2025-09-15
- Pages
- 467-473
- Cited by
- 24
- References
- 6
- Funders
- U.S. Department of Energy
- Battelle
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: PROV-AGENT: Unified Provenance for Tracking AI Agent Interactions in Agentic Workflows. https://app.cochat.ai/papers/10.1109/escience65000.2025.00093
- The paper
- Souza, R., Gueroudji, A., DeWitt, S., Rosendo, D., Ghosal, T., Ross, R., Balaprakash, P., & Da Silva, R. F. (2025). PROV-AGENT: Unified Provenance for Tracking AI Agent Interactions in Agentic Workflows. 2025 IEEE International Conference on eScience (eScience). https://doi.org/10.1109/escience65000.2025.00093
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.