A Comprehensive Behavioral Dataset for the Abstraction and Reasoning Corpus
Abstract The Abstraction and Reasoning Corpus (ARC) is a visual program synthesis benchmark designed to test out-of-distribution generalization in machines. Comparing AI algorithms to human performance is essential to measure progress on these problems. In this paper, we present H-ARC (Human-ARC): a...
Saved in:
| Main Authors: | Solim LeGris, Wai Keen Vong, Brenden M. Lake, Todd M. Gureckis |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-08-01
|
| Series: | Scientific Data |
| Online Access: | https://doi.org/10.1038/s41597-025-05687-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Correction: A Comprehensive Behavioral Dataset for the Abstraction and Reasoning Corpus
by: Solim LeGris, et al.
Published: (2025-08-01) -
Abstract visual reasoning based on algebraic methods
by: Mingyang Zheng, et al.
Published: (2025-01-01) -
Spanish Abstract Meaning Representation: Annotation of a General Corpus
by: Shira Wein, et al.
Published: (2022-11-01) -
Examining the application of nominalization in segmented abstracts: a corpus-based study
by: Yuan Yuwei
Published: (2022-12-01) -
Knowledge Graph as Pre-Training Corpus for Structural Reasoning via Multi-Hop Linearization
by: Wooyoung Kim, et al.
Published: (2025-01-01)