The 22-paper suite: a reading order
===================================

A plain-English map through the ARC/Eden research programme, honest about which results are strong, which are single-lab, and which are under recompute.

Canonical path: /research/blog/paper-suite-reading-order.html
Author: Michael Darius Eastwood
Research programme: https://doi.org/10.17605/OSF.IO/6C5XB

The 22-paper suite: a reading order Michael Darius Eastwood · Independent AI alignment researcher Published 3 July 2026 Michael Darius Eastwood · Overview · 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 ARC/Eden programme is now a suite of twenty-two documents. This note is a reading guide, not a summary. It suggests an order that works for someone starting cold, and it flags where a result is strong, where it is single-lab, and where a headline number is currently under recompute inside the programme itself. Overview · A plain-English reading order for the twenty-two-paper ARC/Eden suite, with honest notes on which results are load-bearing, which are single-lab, and which are under recompute. OSF DOI 10.17605/OSF.IO/6C5XB. The question it asks What order should someone read these papers in if they want to understand what is claimed, what is evidenced, and what is still open? The suite mixes formal mathematics, empirical experiments, methodology work and explicitly philosophical essays. Reading it in the wrong order makes it easier to overclaim on someone's behalf than to understand it. What it found Start with the Executive Summary and the Foundational paper. Those two set the vocabulary. Then read Paper I on the ARC principle and Paper II on the experimental validation, noting the retraction of the earlier unblinded single-model exponent of about 2.24, corrected to about 0.49 across architectures under blinding. Paper III on the alignment scaling problem comes next; its metabolic-scaling headline figures are under recompute and unreconciled inside the programme, and should be treated accordingly. The Paper IV suite is best read as a block: IV-a on baked-in versus computed alignment, IV-b on alignment saturation at low depth, IV-c on the ARC-Align benchmark, and IV-d on the blinding sign-flip. Paper IV-d is the methodological warning that colours everything else.

---
Machine-readable companion. Cite: Eastwood, M. D. (2026). "The 22-paper suite: a reading order". /research/blog/paper-suite-reading-order.html