# The WHY in Business Processes: Unification of Causal Process Models

arXiv: https://arxiv.org/abs/2505.22871 · HTML: https://mlsanity.com/paper/2505.22871/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 28 references that are in the map.
- First posted on arXiv 28 May 2025.

## Builds on (most cited first, 6 of 6)

- [A Survey on Causal Inference](https://mlsanity.com/paper/2002.02770/) (2020)
- [AI-Augmented Business Process Management Systems: A Research Manifesto](https://mlsanity.com/paper/2201.12855/) (2022)
- [Process Mining Meets Causal Machine Learning: Discovering Causal Rules from Event Logs](https://mlsanity.com/paper/2009.01561/) (2020)
- [When to intervene? Prescriptive Process Monitoring Under Uncertainty and Resource Constraints](https://mlsanity.com/paper/2206.07745/) (2022)
- [An Explainable Decision Support System for Predictive Process Analytics](https://mlsanity.com/paper/2207.12782/) (2022)
- [The WHY in Business Processes: Discovery of Causal Execution Dependencies](https://mlsanity.com/paper/2310.14975/) (2023)

## Built on by (most cited first, 1 of 1)

- [Agentic Business Process Management: A Research Manifesto](https://mlsanity.com/paper/2603.18916/) (2026)

## Abstract (arXiv)

Causal reasoning is essential for business process interventions and improvement, requiring a clear understanding of causal relationships among activity execution times in an event log. Recent work introduced a method for discovering causal process models but lacked the ability to capture alternating causal conditions across multiple variants. This raises the challenges of handling missing values and expressing the alternating conditions among log splits when blending traces with varying activities. We propose a novel method to unify multiple causal process variants into a consistent model that preserves the correctness of the original causal models, while explicitly representing their causal-flow alternations. The method is formally defined, proved, evaluated on three open and two proprietary datasets, and released as an open-source implementation.