# Datasets for Studying Generalization from Easy to Hard Examples

arXiv: https://arxiv.org/abs/2108.06011 · HTML: https://mlsanity.com/paper/2108.06011/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 0 of its 2 references that are in the map.
- First posted on arXiv 13 Aug 2021.

## Built on by (most cited first, 12 of 12)

- [Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision](https://mlsanity.com/paper/2312.09390/) (2023)
- [Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach](https://mlsanity.com/paper/2502.05171/) (2025)
- [Path Independent Equilibrium Models Can Better Exploit Test-Time Computation](https://mlsanity.com/paper/2211.09961/) (2022)
- [End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking](https://mlsanity.com/paper/2202.05826/) (2022)
- [A Configurable Library for Generating and Manipulating Maze Datasets](https://mlsanity.com/paper/2309.10498/) (2023)
- [Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization](https://mlsanity.com/paper/2409.18433/) (2024)
- [Planning in a recurrent neural network that plays Sokoban](https://mlsanity.com/paper/2407.15421/) (2024)
- [Rethinking Deep Thinking: Stable Learning of Algorithms using Lipschitz Constraints](https://mlsanity.com/paper/2410.23451/) (2024)
- [On Logical Extrapolation for Mazes with Recurrent and Implicit Networks](https://mlsanity.com/paper/2410.03020/) (2024)
- [FLOWGEN: Fast and slow graph generation](https://mlsanity.com/paper/2207.07656/) (2022)
- [LA-Sign: Looped Transformers with Geometry-aware Alignment for Skeleton-based Sign Language Recognition](https://mlsanity.com/paper/2603.29057/) (2026)
- [AdaStop: Cost-Aware Early Stopping for DNN Test Selection](https://mlsanity.com/paper/2607.05461/) (2026)

## Abstract (arXiv)

We describe new datasets for studying generalization from easy to hard examples.