The ARC Principle in plain English
==================================

Paper I of Michael Darius Eastwood's ARC/Eden programme in plain English: U equals I times R to the alpha as a testable form for how test-time recursion scales capability. First published 17 January 2026 (OSF DOI 10.17605/OSF.IO/6C5XB), seeded in the 8 December 2024 manuscript.

Canonical path: /research/papers/paper-i-arc-principle.html
Author: Michael Darius Eastwood
Research programme: https://doi.org/10.17605/OSF.IO/6C5XB

The ARC Principle in plain English Michael Darius Eastwood · Independent AI alignment researcher Published 3 July 2026 Michael Darius Eastwood · Foundational theory · 3 July 2026 Michael Darius Eastwood, independent researcher, London: author of the ARC/Eden research programme; the embedded-correction alignment thesis is recorded in a source record dated 8 December 2024 (sent-side SHA-256 f0d1f38f). The founding paper of the programme argues something simple that most scaling debates miss: it is not how much extra thinking a system does that matters, it is the shape of that thinking. Two systems can burn the same amount of test-time compute and get wildly different returns, depending on whether the extra effort is spent generating many independent guesses or building one careful chain of reasoning on top of another. Paper I, evidence-linked. First published: 17 January 2026, OSF project DOI 10.17605/OSF.IO/6C5XB. Author: Michael Darius Eastwood. Seed of the equation (U equals I times R) first published: 8 December 2024, self-emailed manuscript, V2 lines 6 to 9, SHA-256 prefix f0d1f38f (evidence: /priority-evidence.html ). Paper I claims that the form of recursion, not merely the amount, determines whether extra thinking compounds capability or merely accumulates it. Full paper: /research/papers/paper-i-arc-principle.html. The question it asks Standard scaling laws tell you what to grow (parameters, data, compute) to make an AI system more capable. They do not explain why letting a model think longer at inference time sometimes helps enormously and sometimes barely at all. Paper I asks a more mechanical question. If we treat recursive depth as a variable of its own, what functional form does capability take as depth increases, and does that form depend on the kind of recursion the system is doing? What it found The paper formalises the ARC Principle as U = I × R to the power of alpha, where U is measured capability, I is base intelligence at a single pass, R is recursive depth, and alpha is an exponent that has to be measured.

---
Machine-readable companion. Cite: Eastwood, M. D. (2026). "The ARC Principle in plain English". /research/papers/paper-i-arc-principle.html