Description / Abstract: Trust in the Dark is an agent-based study, with a pre-registered Python/NumPy simulatorsuite, of how a system keeps a true-enough model of a partly-hidden, drifting, andadversarial world — the problem of *map fidelity*. It is one part of a wider program (the comparative cybernetics of fidelity) and ships with a master overview tying it toits sibling deposits. The central methodological constraint is that an agreeableinstrument is a liability as a verifier: every load-bearing claim is pre-registered withan explicit kill condition before it is run, results are reported including nulls, andthe work is released to be broken. Robust, reproducible findings include: coverage is the master variable (full coveragerescues any prior) ; blind optimism and blind paranoia frame-lock identically;cooperative vetting has an overlap optimum (φ\* ≈ 0. 25) ; disagreement-based vetting haszero leverage against correlated, out-of-frame (Outside-Context-Problem) corruption; anon-adversarial substrate corruptor is catchable only when identification is paired withdurable out-of-band grounding; and a navigation "keystone" in which a position estimategates a value estimate, so that an upstream frame error becomes coherent downstreamcorruption. The deposit is falsification-first. It records what was tested, what was killed (acontrol-theoretic windup–framelock identity; a "sharp threshold" that finer samplingrevealed as a gradual sigmoid; early-warning signatures that proved to be trivialnoise-scaling; a third "saturation" attack class that collapsed into an existing oneunder a pre-registered test), and what remains asserted. A COVERAGEMAP, aREFEREECHANGELOG, verified CITATIONS, and a BREAKTHIS open-falsification challengetravel with the code. Status: self-deposited, AI-assisted (a bound, adversarial procedure-runner), notpeer-reviewed and not awaiting review. The simulator results stand on reproducible runsregardless of how much of the conceptual scaffold is eventually built or retired. Companion to the author's Frame-Lock / Red Queen's Prison and Turtles deposits and to theComparative Biosonar & Navigation work.
Matthew Schulz (Fri,) studied this question.