3rd Workshop on Beyond Attribute-Value Case Representation (BEAR)

This workshop aims to explore foundational advancements in Case-Based Reasoning (CBR) with a particular focus on developing complex and expressive case representations that transcend traditional attribute-value structures. While this year’s ICCBR conference theme, “Generative AI and CBR”, provides a compelling backdrop, our primary goal is to examine the methodologies and representations that can serve as a foundation for the deeper integration of CBR with generative AI in the future. We encourage contributions that investigate novel approaches to case representation, retrieval, and reuse, emphasizing how these can support more complex reasoning tasks. Of particular interest are demonstrations, use cases, and practical implementations showcasing how advanced representations can improve the flexibility and scalability of CBR systems. The workshop will include dedicated demo sessions where participants can present their working systems and applications. While submissions addressing generative AI are welcome, we specifically aim to foster discussions around the theoretical and practical innovations required to prepare CBR for future integration with emerging AI paradigms. By focusing on the fundamental aspects of CBR methodology and representation, this workshop seeks to advance our understanding of how to model and reason about complex cases, creating a solid foundation for future developments at the intersection of CBR and generative AI.

Therefore, the 3rd BEAR workshop discusses research work, CBR applications, and systems where typical attribute-value case representations reach their limits and complex case representations such as object-oriented, textual, graph-structured, time-oriented (time series), hierarchical or hybrid representations need to be used as well as practical applications of such case representations, that imply necessary (research) challenges. In general, these challenges affect all phases of the CBR cycle. For example, complex case representation impacts the performance of similarity-based retrieval and adaptation. In addition, it affects the use of other AI methods integrated with CBR. In this workshop, participants shall present their research with complex case representations focusing on general challenges and the impact on the CBR phases or on the application of such representations. The workshop aims to foster collaboration and exchange of ideas among researchers, developers, and others who use complex case representations that go beyond attribute-value case representations.  

Contributions should be in areas that include, but are not limited to, the following topics: 

• Hybrid AI for Complex Case Representation (e.g., Machine Learning, Deep Learning, and Generative AI such as Large Language Models)

• Representation, Authoring, Elicitation, and Visualization of Complex Case Representations (Text, Graphs, Workflows/Processes, Plans, Time Series Data, IoT Sensor Data, etc.)

• Similarity-Based Retrieval Methods for Complex Cases

• Learning of Similarity Measures

• Adaptation Methods for Complex Case Representation, Transfer Learning

• Explainability, Cognition Approaches for Complex Case Representations

• Evaluation of CBR Systems using Complex Case Representations 

• Methods for Supporting Users in the Revise-Phase, User Experience

• Tools and Techniques for the Retainment of Complex Cases, Maintenance

• Application Scenarios and Use Cases for Complex Cases (such as Medical or Educational Applications, Software Engineering, Administration, Gaming, etc.)

• CBR Frameworks, or Systems supporting Complex Case Representations or Using Real-World Data