Home Research Papers Test log

Papers

Mardenic publishes the reasoning behind its work, not just the result. Each paper states its sources, its method, and the limit of what it establishes. The first comes out of Nullmoor, and it claims no more than the runs behind it support.

01

Checking the cage: a run-time seal model for AI evaluation sandboxes

Published Sep 2026

The first paper out of Nullmoor: the catalogue of 48 escape routes a sandbox has to close, the rule that every probe must be able to fail, and the five false seals we found by attacking our own checker. Coverage is stated as a fraction — 36 of 48 routes fully watched — with the uncovered remainder named rather than rounded away. A paper that reports only successes is not a paper.