CIF certifies interventional interpretability metrics as bounded causal means with anytime-valid confidence sequences, including under adaptive sampling, cutting certification cost 10–30× with betting sequences.
Proceedings of The 35th Uncertainty in Artificial Intelligence Conference , pages =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
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.
citing papers explorer
-
Certified Interventional Fidelity: Anytime-Valid, Adaptive Evaluation of Causal Claims in Mechanistic Interpretability
CIF certifies interventional interpretability metrics as bounded causal means with anytime-valid confidence sequences, including under adaptive sampling, cutting certification cost 10–30× with betting sequences.
-
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.