Process mining aims to identify relevant process characteristics and patterns based on available process artifacts such as event logs, process models, or textual descriptions. To support holistic process analysis, the process mining landscape strives to support the entire process data lifecycle, providing algorithmic and data- driven solutions for tasks ranging from automated process discovery, conformance and compliance analysis, to predictive monitoring, process redesign and data visualisation.

In practice, this idealised image does not always hold up. Data is often imperfect, incomplete, or biased. Algorithms rely on hidden assumptions, unknown errors, or misaligned heuristics. Similarly, the presentation and interpretation of results can be faulty. Issues stemming from individual steps in the process mining pipeline ripple through the analysis, inhibiting reliable and valid outcomes. It is imperative to consider these issues when building algorithms or applying process mining in practise. Furthermore, experimental research in process mining frequently relies on a narrow selection of event logs or imperfect metrics, resulting in findings that lack generalisability and robustness across diverse, real-world processes.

Robust and Resilient Process Mining

…aims to explicitly consider and confront such issues: individually or conjunctively. Here, with robustness, we refer to the ability of systems, algorithms, or techniques to prevent issues stemming from faulty, erroneous data, or uninformed use. Conversely, resilience refers to the ability of such systems, algorithms, or techniques to react to or recover from such factors. Considering both aspects ensures that intents, purposes, and assumptions of data, algorithms, and algorithmic pipelines are properly recognised, accounted for, and taken into account in practice, research, and development. Doing so, ensures valid and reliable insights, which ultimately enables the safe applicability of process mining “in the wild”.

The aim of the workshop is to disseminate and discuss various aspects of robust and resilient process mining. The workshop shall sensitise participants towards the importance of these aspects, and shall provide a space for topics related to the validity, reliability, applicability, and effective use of process mining solutions. This 1st edition of the workshop will be co-located with the 8th International Conference on Process Mining, ICPM’27.

Potential Topics

We invite submissions relating to the design, analysis, or usage of robust and resilient process mining techniques and pipelines. Accordingly, the workshop welcomes submission on the following (or related) topics:

  • Data quality management: defining, detecting, quantifying and repairing data quality issues.
  • Algorithmic robustness and resiliency: algorithms and techniques (for case-based or object-centric event data) that yield reliable results in the presence of erroneous, or unintended inputs, or when applied to novel scenarios
  • Ensuring analytical validity: measuring, quantifying, and identifying potential analysis issues and threats to validity.
  • Process representativeness, observability of processes, event log representativeness, sample-based process mining, assessing the fit of process artifacts for analysis questions
  • Data governance, data traceability, provenance, and the responsible application of process mining.
  • The effective and reliable communication and visualisation of data and analysis result
  • Robust and resilient process mining pipelines, the effective use of process mining, the process of process mining
  • Reproducibility and reliability of analysis results, and experimental pipelines.
  • Robust and resilient integration of generative AI in process mining applications, including LLMs and agents
  • Evaluation frameworks, sensitivity analysis, ablation studies, and research validity in process mining.
  • Benchmarks assessing facets of robustness and resilience of process mining algorithms, and corresponding metrics.
  • Case studies illustrating the impact of data quality, data preprocessing, uncertainty, representativeness, etc. on process mining results.

We encourage all technical, theoretical, and empirical submissions that deal with the design, analysis, or evaluation of robust, reliable, valid, and resilient process mining solutions.

Submission Guidelines

Submissions must use the Springer LNCS/LNBIP format (Found here). Submissions must be in English and cannot exceed 12 pages (including tables, figures, the bibliography, and appendices). Each paper should contain a short abstract, clarifying the relation of the paper with the main topics (preferably using the list of topics above), clearly stating the problem being addressed, the goal of the work, the results achieved, and the relation to other work. Papers should be submitted electronically as a self-contained PDF file via the submission system. When submitting your paper in the submission system, please select the name of the workshop track, “Robust and Resilient Process Mining.” Submissions must be original contributions that have not been published or submitted to other conferences or journals in parallel with this workshop.

Springer will publish all workshop papers as a post-workshop proceedings volume in the Lecture Notes in Business Information Processing (LNBIP) series.

At least one author of each accepted paper must register and participate in the workshop. Please visit the main conference website for more information.

Workhop Program

TBA

Important Dates

  • Author Abstract Submission: November 11, 2026 (AoE)
  • Author Paper Submission: November 18, 2026 (AoE)
  • Author Paper Acceptance Notification: December 21, 2026 (AoE)
  • Author Pre-workshop Camera-Ready Papers: January 21, 2027 (AoE)
  • Workshops: February 8, 2027
  • Post-workshop Camera-Ready Papers: February 22, 2027

Workshop Organizers

Yannis Bertrand is an assistant professor in the business informatics research group at Hasselt University. He received the PhD degree from KU Leuven (Belgium) in 2024 with a thesis titled “Enhancing process mining with IoT data”. Then, he was a post-doctoral researcher at Ghent University from 2024 to 2025, where he continued building his research lines around process analysis with complex data. His research interests include IoT-aware process analysis, data engineering and data quality.

Martin Kabierski is a postdoctoral researcher at the faculty of computer science at University of Vienna. He received his PhD from Humboldt-Universit¨at zu Berlin (Germany) in 2025. His research interests involve the representativeness of event data, statistical process analysis, and data quality issues.

Jari Peeperkorn is a postdoctoral researcher working on an FWO grant at KU Leuven. He received his PhD from KU Leuven in 2023. His research interests include machine learning, predictive process monitoring, algorithmic contributions to process mining, and investigative research on algorithmic capa- bilities.

Gyunam Park is an assistant professor in the process analytics cluster at the department of mathematics and computer science, Eindhoven University of Technology. He received his Ph.D. in computer science from RWTH Aachen University (Germany) in 2024. His research interests include process mining methods that provide transparency over processes and help stakeholders charac- terise critical process problems, as well as responsible machine learning methods for process-related problems.

Shazia Sadiq is a professor at the University of Queensland and a globally recognised leader in data and process management, with a 25-year career as a researcher and educator focused on dismantling socio-technical barriers to technology-driven transformation. Her research interests include data quality management, scalable data curation process modelling and compliance, and information resilience.

Program Committee

TBA

For further information do not hesitate to contact the workshop organizers at r2pm-2027@easychair.org.