You're currently viewing an old version of this dataset. To see the current version, click here.

Abstraction and Reasoning Corpus (ARC)

A collection of heterogeneous visual reasoning data sets and an interesting benchmark for two reasons: First, visual reasoning programs tend to be large (in current program synthesis context) and are out of reach for existing synthesis techniques. Second, visual domains offer an intuitive notion of analogy between objects based on their visual properties and relational context (i.e. spatial positioning).

Data and Resources

Cite this as

Andrew Cropper, Sebastijan Dumancic (2024). Dataset: Abstraction and Reasoning Corpus (ARC). https://doi.org/10.57702/t3mvg9u9

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2301.03094
Citation
  • https://doi.org/10.48550/arXiv.2405.15880
Author Andrew Cropper
More Authors
Sebastijan Dumancic
Homepage https://www.kaggle.com/c/ARC