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 Third Conference on Causal Learning and Reasoning , 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
Task-aligned supervised geometric stability predicts linear steerability with high accuracy while unsupervised stability detects representational drift earlier and with lower false alarms than CKA or Procrustes.
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.
-
The Geometric Canary: Predicting Steerability and Detecting Drift via Representational Stability
Task-aligned supervised geometric stability predicts linear steerability with high accuracy while unsupervised stability detects representational drift earlier and with lower false alarms than CKA or Procrustes.