Resist and Update: Counterfactual Report Coordinates for Incentive-Compatible LLMs

The method identifies separate activation coordinates for answers, confidence, and caveats, then clamps reports against an incentive-neutralized counterfactual. Its two-pass form reached **1.00 resist and 1.00 update** on a Bayesian-witness benchmark.

For agents making consequential judgments, test two behaviors separately: refusing unsupported pressure and changing when real evidence arrives. Resist-only tuning can suppress legitimate updates, while explicitly training both objectives performed better here.

The two-pass result is a causal certificate under a constructible reference, not a deployment recipe. The single-pass compilation fell to **0.73 resist and 0.97 update**, despite reproduction across **three model families** and transfer to SycophancyEval.