Authors create a benchmark across discrete/continuous and static/dynamical systems and introduce the Causal Abstraction Error (CAE) metric that reliably distinguishes valid from invalid causal abstractions when it includes faithfulness testing.
arXiv preprint arXiv:2311.18639 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Validating Causal Abstraction Metrics on Simulated Complex Systems
Authors create a benchmark across discrete/continuous and static/dynamical systems and introduce the Causal Abstraction Error (CAE) metric that reliably distinguishes valid from invalid causal abstractions when it includes faithfulness testing.