A plausible answer is not the same as a grounded answer.
Superretometer is a cognitive harness that makes reasoning visible, traceable, and testable — so you can ask: what does this conclusion depend on, and what makes those dependencies real?
An AI system or engineering simulation can produce a result that looks correct. The numbers close. The chain of reasoning appears sound. Yet the conclusion rests on premises that have no independent grounding in the physical world.
Consider a reasoning chain from an engineering model:
The chain is structurally valid. But which elements are independently grounded?
Superretometer makes the last distinction explicit, structural, and computable.
Superretometer harnesses four foundations into a single reasoning and verification loop:
LLM provides the generative reasoning capability — forming hypotheses, traversing domains, constructing candidate chains of justification.
Emergent Memory gives persistent storage across sessions: evidence, observations, decisions, and validated knowledge do not decay when the conversation ends.
CAFCR and Lines of Reasoning impose structure on the reasoning chain: each step records claim, viewpoint, and knowledge objects used. The thread becomes auditable and restartable.
Inspired by the EPR completeness criterion: a conclusion is warranted only if the elements carrying it possess independently grounded counterparts. Not a quantum-mechanical claim — an epistemic one.
A simulation result is a file on disk. It is not a conclusion. The four-gate SimulationGatePolicy determines whether a simulation-backed claim may carry a design decision.
All four gates must PASS for design-bearing. One BLOCK means informative only — not that the simulation failed, but that the warrant chain is incomplete.
Superretometer is assembled from four complementary ingredients. The work originated through the contributions of Nikolai Fasting and Maciej Kucharz at Emergent Company, who built Emergent Memory and Emergent Strategy — the persistent reasoning and adaptive planning substrate this harness runs on.
Emergent Memory provides the persistent graph backbone: knowledge, evidence, decisions, and observations survive across sessions, failures, and revisions. Without persistence, reasoning cannot accumulate.
Emergent Strategy closes the adaptive loop: act → observe → learn → revise → act again. Developed by Nikolai Fasting and Maciej Kucharz at Emergent Company. Emergent Strategy is grounded in Nikolai's experience building over 30 startups and inspired by Ready, Fire, Aim (Robert Chapman, 2008): bias toward action, learn from outcome, iterate.
Together they form the cognitive base: reasoning with continuity and adaptive learning.
Müller's CAFCR: A Cognitive Approach for Flexibly Coordinating Reasoning (PhD thesis, University of Twente, 2004) introduced Lines of Reasoning — a structured method for tracing decisions from the user's need, through viewpoints, to a bill of materials (realization). Viewpoint-based traversal connects each layer so the reasoning chain can be audited and restarted at any step.
Superretometer's Thread model computationally applies the principle of CAFCR Lines of Reasoning. Each thread records claims, viewpoints, and the knowledge objects used — making reasoning auditable and restartable.
Müller's later work on CEMA/CESA and viewpoint hopping further informed the structure of explicit engineering reasoning threads.
Architectural Reasoning; CAFCR · CAFCR Thesis PDF · Overview of CAFCR and Threads of Reasoning
Can Quantum-Mechanical Description of Physical Reality Be Considered Complete? (Physical Review, 47, 777, 1935) proposed a criterion of reality and argued that a complete theory must account for every element of physical reality.
Superretometer adapts this as an epistemic criterion for engineering reasoning: a conclusion is warranted only if the quantities and claims carrying it possess independently grounded counterparts outside the model.
This is our analogy, not a claim about quantum mechanics. We do not apply quantum physics to engineering problems. We apply the structural question EPR asked about the relationship between description and reality.
The Harness-of-Harness framework (Yan et al., 2026) provides supporting evidence that structuring a harness around an LLM matters — for state preservation, progressive disclosure, and long-running orchestration.
It is not the conceptual origin of Superretometer. It validates the architectural direction.
Superretometer is inspired by and builds on these traditions. It is not affiliated with or endorsed by the original authors or organizations.
These mechanisms — persistent structured reasoning, explicit provenance tracing, and independent grounding verification — may also be relevant to the broader question of how AI systems can maintain testable, non-decaying models of the physical world.
The Cognitive Harness specification and the Superretometer reference implementation are on GitHub.
github.com/euthm/superretometer
Specification: spec/ ·
Reference implementation: cognitive_harness/ ·
Examples: examples/ ·
Tests: tests/