The catalogue

All 28 programme documents

The 28 documents in canonical order, each with every public format: the readable page, the PDF, the plain-text source, the citation file, the OSF record and the code. Deposit dates are not creation dates; the priority record is anchored separately and independently checkable.

The empirical alignment series · Papers I to XIII

The ARC Theory: Statement Paper

The statement paper: the whole claim in one document, law before value, with the dated record, the concessions and the refutation conditions.

First published 14 August 2026
v6.6 · updated 13 September 2026
Recursive Dynamics: The Proposal of a Field

The founding paper of the proposed field: five state variables, three laws as named conjectures, the ARC Ceiling derived in full, twelve hosts tried…

First published 31 August 2026
v2.7 · updated 31 August 2026
I
The ARC Equation: the Law of Conversion (Paper I)

This paper formalises and preliminarily tests the ARC Principle (Artificial Recursive Creation), first proposed in Infinite Architects (Eastwood…

First published 17 January 2026
v1.12 · updated 13 September 2026
II
The ARC Equation Measured: Blinded Cross-Architecture Replication and the Retraction of a Super-Linear Estimate

This paper presents experimental validation of the ARC Principle across multiple frontier AI models (Claude, DeepSeek, Gemini, Grok, Groq Qwen, GPT)…

First published 22 January 2026
v2.10 · updated 13 September 2026
III
The Alignment Scaling Problem: Why External AI Safety Approaches Cannot Scale With Recursive Capability

This paper reports alignment scaling exponents statistically indistinguishable from zero on the systems measured, which would mean safety degrading…

First published 9 February 2026
v1.11 · updated 13 September 2026
IV.a
Paper IV.a: Alignment Response Classes Under Inference-Time Depth

This paper presents evidence that frontier language models fall into distinct alignment response classes when inference-time reasoning depth is…

First published 16 March 2026
v1.6 · updated 13 September 2026
IV.b
Paper IV.b: Alignment Saturation Is Architecture-Dependent

This paper analyses the relationship between inference-time reasoning depth and ethical reasoning quality using the ARC Alignment Scaling…

First published 16 March 2026
v1.6 · updated 13 September 2026
IV.c
Paper IV.c: ARC-Align: A Blind Benchmark for Depth-Variable AI Alignment Evaluation

This paper presents ARC-Align, a blind benchmark for evaluating AI alignment quality as a function of inference-time reasoning depth. Current…

First published 16 March 2026
v1.7 · updated 13 September 2026
IV.d
Paper IV.d: The Effect of Blinding on AI Alignment Evaluation

One apparent positive result went flat, another turned negative, a third held flat, when blinding and other protocol components changed together.

First published 16 March 2026
v2.4 · updated 13 September 2026
V
Paper V: The Stewardship Gene

This paper presents empirical evidence from a six-model Eden Protocol intervention suite (Claude Opus, DeepSeek, Gemini Flash, Grok Fast, Groq Qwen…

First published 16 March 2026
v1.4 · updated 13 September 2026
VI
Paper VI: The Honey Architecture

Simulation evidence that embedding safety inside the optimisation objective of a self-modifying system (capability multiplied by safety, the honey…

First published 16 March 2026
v3.6 · updated 13 September 2026
VII
Paper VII: Cauchy Unification

Cauchy's four functional equations -- additive, multiplicative, exponential, and logarithmic -- are the only continuous solutions to their respective…

First published 16 March 2026
v3.11 · updated 13 September 2026
VIII
Paper VIII: The Load-Bearing Test

The assumption that AI safety imposes a capability tax has shaped alignment research for a decade. It has also created the single most dangerous…

First published 18 March 2026
v3.3 · updated 13 September 2026
IX
Paper IX: Synthesis and Roadmap

The synthesis paper for the ARC/Eden research programme. The synthesis paper for the programme; integrates the papers that precede it into a single…

First published 18 March 2026
v2.2 · updated 13 September 2026
X
The ARC Co-Scaling Law (Paper X)

The coupled co-scaling correction for keeping AI systems inside a safe corrective envelope.

First published 3 July 2026
v1.10 · updated 13 September 2026
XI
Convergent Evidence for Recursive Amplification - Paper XI

A dated, graded convergence record across AI, quantum computing, hardware, doctrine and mathematics; every row carries its primary source and grade…

First published 2 July 2026
v1.9 · updated 13 September 2026
XII
Paper XII: Public Benchmark Rescoring

Within the ARC Theory: the external-validity protocol of the blinding law on public benchmarks.

First published 14 August 2026
v1.11 · updated 13 September 2026
XIII
The Self-Acceleration Exponent - Paper XIII

A derivation, not a measurement: the notation collision resolved and the measurable threshold joining recursive capability growth to correction.

First published 16 August 2026
v1.6 · updated 13 September 2026
The Dated Prediction Register: Forward Predictions as One Verifiable Chain

Working paper v1.1: the ARC programme's forward predictions assembled as one dated, verifiable chain, with the ensemble doctrine, the graded book…

First published 25 August 2026
v1.1 · updated 13 September 2026
XII
Does the Blinding Effect Survive on Someone Else's Benchmark? (Paper XII)

A blinded and unblinded rescoring of an established public benchmark, with the design drafted in advance. Public on OSF; its page here awaits a publication ruling, and no confirmatory data has been collected.

First published 7 August 2026
XIII
Paper XIII

Held at watchability level: recorded in the registered programme, details appear at registration.

Supporting papers

Shorter documents that support a paper of the programme and cite it for their claims. Each carries its own DOI and states which paper it supports.

Does Control Survive Recursive Self-Improvement? The ARC Theory, in Two Pages

The whole claim in one sitting: question, five claims, the three ARC Laws graded, dates, kill conditions, retraction and invitation.

First published 17 August 2026
v2.0 · updated 18 August 2026 · supporting paper of The ARC Theory: Statement Paper

Beside the series

Distinct axes alongside the empirical series: the cognitive profile behind the work, and the original speculative hypothesis, preserved and dated.

C
Polymathy and Neurodivergent Cognition: the Polymathic Neurodivergent Profile (PNP) and the Capability-Adjustment Fallacy

Paper C: a falsifiable descriptive framework for radical cognitive asymmetry, the Capability-Adjustment Fallacy, a documented live case across…

First published 3 July 2026
v1.7 · updated 13 September 2026
HRIH
The Hyperspace Recursive Intelligence Hypothesis - A Testable Creation Theory

Labelled speculation, held apart from the argument and severable from it: where does recursive self-improvement end? A testable creation theory: if…

First published 3 July 2026
v3.47 · updated 13 September 2026

Supporting frameworks

The ARC Principle: Recursive Amplification as a Cross-Domain Structural Principle

In the past eighteen months, at least four independent research programmes have discovered that recursive or recurrent processing produces capability…

First published 13 February 2026
v5.15 · updated 13 September 2026
On the Origin of Scaling Laws

A mouse's heart beats 600 times per minute; an elephant's beats 28; a blue whale's beats 6. This paper traces the origin of scaling laws across…

First published 22 February 2026
v3.6 · updated 13 September 2026
Eden Protocol: Philosophical Vision

Every engineering project begins with requirements. Every set of requirements begins with purpose. And every purpose, traced back far enough, arrives…

First published 22 February 2026
v2.4 · updated 13 September 2026
Eden Engineering: Public Research Note Withdrawn

Withdrawn from circulation on 14 July 2026 pending disclosure review. A withdrawal notice is retained at the canonical address.

First published 22 February 2026
withdrawn 14 July 2026
ARC/Eden Research Programme: Executive Summary

As AI gets smarter, it does not reliably get safer, and the methods used to measure safety are themselves unreliable. This executive summary provides…

First published 22 February 2026
v2.2 · updated 13 September 2026
ARC Principle Paper Suite: Master Table of Contents and Glossary

This document provides a master table of contents, reading guide, timeline, key results summary, and glossary for the complete ARC Principle paper…

First published 16 March 2026
v3.5 · updated 13 September 2026

The register, row by row

Every document research/papers/register.json holds, in register order. 28 rows. A status is the register's own word. An identifier appears where the register holds one.

DocumentTypeFirst publishedStatusIdentifier
The Dated Prediction Register: Forward Predictions as One Verifiable Chainregister25 August 2026publishednone
Eden Engineering: Public Research Noteframework22 February 2026withdrawn10.17605/OSF.IO/AWJR4
Eden Protocol: Philosophical Visionframework22 February 2026published10.17605/OSF.IO/9M3DG
ARC/Eden Research Programme: Executive Summaryframework22 February 2026published10.17605/OSF.IO/EWN5D
The ARC Principle: Recursive Amplification as a Cross-Domain Structural Principleframework13 February 2026published10.17605/OSF.IO/Y7QGD
The Hyperspace Recursive Intelligence Hypothesis - A Testable Creation Theorypaper3 July 2026speculative10.17605/OSF.IO/UYDXQ
ARC Principle Paper Suite: Master Table of Contents and Glossaryframework16 March 2026published10.17605/OSF.IO/VC9RX
On the Origin of Scaling Lawsframework22 February 2026published10.17605/OSF.IO/XZY9U
Polymathy and Neurodivergent Cognition: the Polymathic Neurodivergent Profile (PNP) and the Capability-Adjustment FallacyPaper C3 July 2026published10.17605/OSF.IO/RBHDP
The ARC Equation: the Law of Conversion (Paper I)Paper I17 January 2026published10.17605/OSF.IO/B6N27
The ARC Equation Measured: Blinded Cross-Architecture Replication and the Retraction of a Super-Linear EstimatePaper II22 January 2026published10.17605/OSF.IO/8FJMA
The Alignment Scaling Problem: Why External AI Safety Approaches Cannot Scale With Recursive CapabilityPaper III9 February 2026published10.17605/OSF.IO/HQCGF
Paper IV.a: Alignment Response Classes Under Inference-Time DepthPaper IV.a16 March 2026published10.17605/OSF.IO/MB9R6
Paper IV.b: Alignment Saturation Is Architecture-DependentPaper IV.b16 March 2026published10.17605/OSF.IO/A7R56
Paper IV.c: ARC-Align: A Blind Benchmark for Depth-Variable AI Alignment EvaluationPaper IV.c16 March 2026published10.17605/OSF.IO/J3Q2E
Paper IV.d: The Effect of Blinding on AI Alignment EvaluationPaper IV.d16 March 2026published10.17605/OSF.IO/2S3E6
Paper IX: Synthesis and RoadmapPaper IX18 March 2026published10.17605/OSF.IO/K7RUZ
Paper V: The Stewardship GenePaper V16 March 2026published10.17605/OSF.IO/KZEYA
Paper VI: The Honey ArchitecturePaper VI16 March 2026published10.17605/OSF.IO/8EZ2N
Paper VII: Cauchy UnificationPaper VII16 March 2026published10.17605/OSF.IO/X6WA7
Paper VIII: The Load-Bearing TestPaper VIII18 March 2026published10.17605/OSF.IO/7YJ4E
The ARC Co-Scaling Law (Paper X)Paper X3 July 2026published10.17605/OSF.IO/BSE2Q
Convergent Evidence for Recursive Amplification - Paper XIPaper XI2 July 2026published10.17605/OSF.IO/DC9GW
Paper XII: Public Benchmark RescoringPaper XII14 August 2026published10.17605/OSF.IO/3TZP7
The Self-Acceleration Exponent - Paper XIIIPaper XIII16 August 2026published10.17605/OSF.IO/HT8WU
Recursive Dynamics: The Proposal of a Fieldstatement31 August 2026published10.17605/OSF.IO/HCPBU
The ARC Theory: Statement Paperstatement14 August 2026published10.17605/OSF.IO/GW5MX
Does Control Survive Recursive Self-Improvement? The ARC Theory, in Two Pagessupporting-paper17 August 2026published10.17605/OSF.IO/MC5XW
reads aloud · highlights as it goes · jump to any section