A four-step recipe partitions the input space using interchange intervention behavior to diagnose where causal abstractions hold and to guide improvements, demonstrated by recovering a full hypothesis from scratch in a toy logic task.
interpretability illusion
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Low-rank graphs induce latents that form causal abstractions, with identifiability results and a practical objective enabling unsupervised learning of high-level SCMs from low-level measurements.
citing papers explorer
-
Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction
A four-step recipe partitions the input space using interchange intervention behavior to diagnose where causal abstractions hold and to guide improvements, demonstrated by recovering a full hypothesis from scratch in a toy logic task.
-
Unsupervised Causal Abstractions Discovery
Low-rank graphs induce latents that form causal abstractions, with identifiability results and a practical objective enabling unsupervised learning of high-level SCMs from low-level measurements.