# Kandinsky Patterns

arXiv: https://arxiv.org/abs/1906.00657 · HTML: https://mlsanity.com/paper/1906.00657/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2019.

## Built on by (most cited first, 16 of 16)

- [Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions](https://mlsanity.com/paper/2310.19775/) (2023)
- [BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts](https://mlsanity.com/paper/2402.12240/) (2024)
- [A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts](https://mlsanity.com/paper/2406.10368/) (2024)
- [Neuro-Symbolic Forward Reasoning](https://mlsanity.com/paper/2110.09383/) (2021)
- [Greybox XAI: a Neural-Symbolic learning framework to produce interpretable predictions for image classification](https://mlsanity.com/paper/2209.14974/) (2022)
- [Learning Differentiable Logic Programs for Abstract Visual Reasoning](https://mlsanity.com/paper/2307.00928/) (2023)
- [A survey on knowledge-enhanced multimodal learning](https://mlsanity.com/paper/2211.12328/) (2022)
- [KANDINSKYPatterns -- An experimental exploration environment for Pattern Analysis and Machine Intelligence](https://mlsanity.com/paper/2103.00519/) (2021)
- [The KANDY Benchmark: Incremental Neuro-Symbolic Learning and Reasoning with Kandinsky Patterns](https://mlsanity.com/paper/2402.17431/) (2024)
- [Neural Meta-Symbolic Reasoning and Learning](https://mlsanity.com/paper/2211.11650/) (2022)
- [Study on the Helpfulness of Explainable Artificial Intelligence](https://mlsanity.com/paper/2410.11896/) (2024)
- [Logical Assessment Formula and Its Principles for Evaluations with Inaccurate Ground-Truth Labels](https://mlsanity.com/paper/2110.11567/) (2021)
- [Right for the Right Reasons: Avoiding Reasoning Shortcuts via Prototypical Neurosymbolic AI](https://mlsanity.com/paper/2510.25497/) (2025)
- [Visual Perceptual to Conceptual First-Order Rule Learning Networks](https://mlsanity.com/paper/2604.07897/) (2026)
- [COCOLogic-V2: Identifying Logical Inconsistencies via Truly Hard-Negatives](https://mlsanity.com/paper/2606.28194/) (2026)
- [Soft Symbol Grounding for Prototypical Concepts](https://mlsanity.com/paper/2609.12247/) (2026)

## Abstract (arXiv)

Kandinsky Figures and Kandinsky Patterns are mathematically describable, simple self-contained hence controllable test data sets for the development, validation and training of explainability in artificial intelligence. Whilst Kandinsky Patterns have these computationally manageable properties, they are at the same time easily distinguishable from human observers. Consequently, controlled patterns can be described by both humans and computers. We define a Kandinsky Pattern as a set of Kandinsky Figures, where for each figure an "infallible authority" defines that the figure belongs to the Kandinsky Pattern. With this simple principle we build training and validation data sets for automatic interpretability and context learning. In this paper we describe the basic idea and some underlying principles of Kandinsky Patterns and provide a Github repository to invite the international machine learning research community to a challenge to experiment with our Kandinsky Patterns to expand and thus make progress in the field of explainable AI and to contribute to the upcoming field of explainability and causability.