ML climate emulators degrade under seasonal distribution shifts that proxy long-term climate change, but physically motivated compositional decompositions improve out-of-distribution performance with modest in-distribution trade-offs.
Inductive biases for deep learning of higher-level cognition
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Supervised deep learning cannot reach symbolic-level syllogistic reasoning due to indistinguishable training data across 24 valid types and contradictory training targets in end-to-end premise-to-conclusion mapping.
citing papers explorer
-
No Epoch Like the Present: Robust Climate Emulation Requires Out-of-Distribution Generalisation
ML climate emulators degrade under seasonal distribution shifts that proxy long-term climate change, but physically motivated compositional decompositions improve out-of-distribution performance with modest in-distribution trade-offs.
-
Data-driven Machine Learning Cannot Reach Symbolic-level Logical Reasoning -- The Limit of the Scaling Law
Supervised deep learning cannot reach symbolic-level syllogistic reasoning due to indistinguishable training data across 24 valid types and contradictory training targets in end-to-end premise-to-conclusion mapping.