# Towards a Simple and Extensible Standard for Object-Centric Event Data (OCED) -- Core Model, Design Space, and Lessons Learned

arXiv: https://arxiv.org/abs/2410.14495 · HTML: https://mlsanity.com/paper/2410.14495/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Oct 2024.

## Built on by (most cited first, 4 of 4)

- [Agentic AI Process Observability: Discovering Behavioral Variability](https://mlsanity.com/paper/2505.20127/) (2025)
- [OCPM2: Extending the Process Mining Methodology for Object-Centric Event Data Extraction](https://mlsanity.com/paper/2503.10735/) (2025)
- [Agent Behavior Mining: Generative AI Agent Governance in Business Processes](https://mlsanity.com/paper/2606.20669/) (2026)
- [A Framework for Object-Centric Predictive Monitoring of Collaborative Processes](https://mlsanity.com/paper/2608.27671/) (2026)

## Abstract (arXiv)

Process mining is shifting towards use cases that explicitly leverage the relations between data objects and events under the term of object-centric process mining. Realizing this shift and generally simplifying the exchange and transformation of data between source systems and process mining solutions requires a standardized data format for such object-centric event data (OCED). This report summarizes the activities and results for identifying requirements and challenges for a community-supported standard for OCED. (1) We present a proposal for a core model for object-centric event data that underlies all known use cases. (2) We detail the limitations of the core model wrt. a broad range of use cases and discuss how to overcome them through conventions, usage patterns, and extensions of OCED, exhausting the design-space for an OCED data model and the inherent trade-offs in representing object-centric event data. (3) These insights are backed by five independent OCED implementations which are presented alongside a series of lessons learned in academic and industrial case studies. The results of this report provide guidance to the community to start adopting and building new process mining use cases and solutions around the reliable concepts for object-centric event data, and to engage in a structured process for standardizing OCED based on the known OCED design space.