Interpretability & Mechanistic Interp - Weekly Roundup

This work proposes online conformal state probing (OCSP), an action and probing policy that certifies worst-case reliability levels without relying on distributional assumptions, and can be applied to existing pre-trained value-based control policies without requiring retraining or fine-tuning.

This work proposes online conformal state probing (OCSP), an action and probing policy that certifies worst-case reliability levels without relying on distributional assumptions, and can be applied to existing pre-trained value-based control policies without requiring retraining or fine-tuning.

Dissociation suggests current neuron-level monosemanticity metrics are insensitive to a class of real interpretability gains, and positions cheap architectural priors as a viable training-time complement to post-hoc tooling.

Governance-as-Code (GaC), a framework of 43 machine-checkable acceptance criteria across six compliance modules that run in a CI/CD pipeline and emit Article-indexed audit evidence, is delivered and the actual Rego policy code is shown, showing the actual Rego policy code rather than merely describing it.

These findings verify the original paper's claim that User Profile Recommendation achieves competitive performance under its test-set reranking protocol and makes recommendations more transparent.

PetriBench is introduced, a compact, fully self-contained, and scalable benchmark for evaluating LLM reasoning over dynamic state spaces using Petri nets, a mature formalism for modeling real-world concurrent and distributed systems.

Robustness controls show that the signal extends beyond English, is not explained solely by accompanying OCR, and depends on paired visual evidence, thus, routing, rather than representation alone, is a recurring bottleneck in harmful meme classification.