Certified Circuits: Stability Guarantees for Mechanistic Circuits
cs.AI, cs.CV, cs.CY
Submitted: 2026-02-26
Updated: 2026-11-04
Code: https://github.com/AlaaAnani/certified-circuits
Terminology
Sources
- Localizing Model Behavior with Path Patching
- Pruning for Feature-Preserving Circuits in CNNs
- Interpretable Disentanglement of Neural Networks by Extracting Class-Specific Subnetwork
- Seeing Through Circuits: Faithful Mechanistic Interpretability for Vision Transformers
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents