Yes to your last question, that is essentially how the first iteration solutions operated. Some of the original kaggle competition’s best solutions used a DSL made of these transformations. That was 4 years ago. [1]
The issue with that path is that the problems aren’t using a programmatic generator. The rule sets are anything a person could come up with. It might be as simple as “biggest object turns blue” but they can be much more complicated.
Additionally, the test set is private so it can’t be trained on or extracted from. It has rules that aren’t in the public sets.
The issue with that path is that the problems aren’t using a programmatic generator. The rule sets are anything a person could come up with. It might be as simple as “biggest object turns blue” but they can be much more complicated.
Additionally, the test set is private so it can’t be trained on or extracted from. It has rules that aren’t in the public sets.
[1] https://www.kaggle.com/competitions/abstraction-and-reasonin...