# Uncertain Process Data with Probabilistic Knowledge: Problem Characterization and Challenges

arXiv: https://arxiv.org/abs/2106.03324 · HTML: https://mlsanity.com/paper/2106.03324/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 7 Jun 2021.

## Builds on (most cited first, 7 of 7)

- [SF-Net: Single-Frame Supervision for Temporal Action Localization](https://mlsanity.com/paper/2003.06845/) (2020)
- [Unsupervised Learning and Segmentation of Complex Activities from Video](https://mlsanity.com/paper/1803.09490/) (2018)
- [Conformance Checking over Uncertain Event Data](https://mlsanity.com/paper/2009.14452/) (2020)
- [Mining Uncertain Event Data in Process Mining](https://mlsanity.com/paper/1910.00089/) (2019)
- [Discovering Process Models from Uncertain Event Data](https://mlsanity.com/paper/1909.11567/) (2019)
- [Efficient Construction of Behavior Graphs for Uncertain Event Data](https://mlsanity.com/paper/2002.08225/) (2020)
- [Efficient Time and Space Representation of Uncertain Event Data](https://mlsanity.com/paper/2010.00334/) (2020)

## Built on by (most cited first, 7 of 7)

- [Conformance Checking Over Stochastically Known Logs](https://mlsanity.com/paper/2203.07507/) (2022)
- [SKTR: Trace Recovery from Stochastically Known Logs](https://mlsanity.com/paper/2206.12672/) (2022)
- [Probabilistic and Non-Deterministic Event Data in Process Mining: Embedding Uncertainty in Process Analysis Techniques](https://mlsanity.com/paper/2205.04827/) (2022)
- [Process Mining on Uncertain Event Data](https://mlsanity.com/paper/2204.04148/) (2022)
- [Alignment-based conformance checking over probabilistic events](https://mlsanity.com/paper/2209.04309/) (2022)
- [DDTR: Diffusion Denoising Trace Recovery](https://mlsanity.com/paper/2510.22553/) (2025)
- [All Eyes on the Workflow: Automated and Efficient Event Discovery from Video Streams](https://mlsanity.com/paper/2604.22476/) (2026)

## Abstract (arXiv)

Motivated by the abundance of uncertain event data from multiple sources including physical devices and sensors, this paper presents the task of relating a stochastic process observation to a process model that can be rendered from a dataset. In contrast to previous research that suggested to transform a stochastically known event log into a less informative uncertain log with upper and lower bounds on activity frequencies, we consider the challenge of accommodating the probabilistic knowledge into conformance checking techniques. Based on a taxonomy that captures the spectrum of conformance checking cases under stochastic process observations, we present three types of challenging cases. The first includes conformance checking of a stochastically known log with respect to a given process model. The second case extends the first to classify a stochastically known log into one of several process models. The third case extends the two previous ones into settings in which process models are only stochastically known. The suggested problem captures the increasingly growing number of applications in which sensors provide probabilistic process information.