ARC / Eden Research Programme · Paper XI · v1.0

Convergent Evidence for Recursive Amplification as a Cross-Domain Structural Principle

Michael Darius Eastwood · Independent AI alignment researcher

Published 2 July 2026

19 independently sourced convergences. Zero shared citations. One structural principle. The closed loop.

Michael Darius Eastwood

Independent Researcher · London, United Kingdom

2 July 2026 · OSF: 10.17605/OSF.IO/6C5XB

ND brain (ADHD+autism, diagnosed)
  → Dec 8 2024 manuscript (DKIM, SHA-256: f0d1f38f)
    → Anthropic confirms at 78% in the RL-training condition (12% baseline) (10 days)
    → 19 independently sourced convergences (18 months)
    → Hernández-Espinosa et al. (PNAS Nexus, Apr 2026)
      argues ND cognition is a protective factor for alignment
      → Gumbau Mezquita (arXiv, Jun 26 2026) reads Hernández
        produces formal undecidability proof
        credits Hernández as "conceptual foundation"
        → proof vindicates Dec 8 framework
          → PNP (Paper C) documents the cognitive architecture
            → Dr Woolley note: clinical documentation
              → LOOP DOCUMENTED END-TO-END. EVERY LINK INDEPENDENTLY CHECKABLE.

1. The 19 Independent Convergences

Register discipline: one external event per row, one primary source per row, hyperlinked to the official source wherever a stable canonical URL exists (arXiv, DOI, publisher, patent office, broadcaster, vendor); press-sourced rows name their outlets and date instead. Gaps are measured from the named artifact date, stated per row. Twelve further candidate rows are held on a source-pending list and are neither counted nor shown until each carries a verifiable primary source; reader engagement with the work (for example gifted copies) is logged separately and never counted as convergence. Priority is credited outward wherever the dates demand it (row 3). The full register with quarantine and engagement lists: michaeldariuseastwood.com/research/evidence-spine.html.

2. Three Degrees of Neurodivergence

Degree 1 - The Researcher (Paper C, PNP). Michael Darius Eastwood. Diagnosed ADHD. Diagnosed autism. Adulthood diagnosis. Brain that connects domains uniform thinkers don't see as adjacent. Builds a 189,000-word framework across domains while representing himself in complex legal proceedings. The PNP (Polymathic Neurodivergent Profile) provides the descriptive clinical framework. Dr Woolley note provides clinical documentation. The method IS the hypothesis.

Degree 2 - The Protection Proof (Hernández-Espinosa et al., 2026, PNAS Nexus). Oxford, King's College London, Alan Turing Institute, University of Tokyo. Gödel/Turing prove external alignment is impossible. Solution: cognitive diversity. Neurodivergent thinking is not a defect. It is the protective architecture. The paper does not cite Eastwood. Does not know he exists. Independently proves his brain type is the instrument alignment requires.

Degree 3 - The Formal Proof (Gumbau Mezquita, 2026, arXiv:2606.28639). University Jaume I, Spain. Reads Hernández-Espinosa. Extends with Trakhtenbrot's Wall. Two formal theorems: Unverifiability of Alignment + Soundness-Completeness-Tractability Trilemma. Credits Hernández as conceptual foundation. Does not cite Eastwood. Independently vindicates his framework.

None of them knew about each other. None planned this. The chain is discovered, not manufactured.

3. The Closed Loop

The closed loop has four structural properties:

1. The method IS the hypothesis. The cognitive architecture that produced the framework - neurodivergent pattern recognition across domains - is the same architecture that Hernández-Espinosa et al. independently proved is the protective factor alignment requires. The researcher is not a person who happens to have a theory. The researcher IS the theory's first evidence. The brain that built it is the brain type the PNAS paper proved the field needs.

2. The framework IS its own evidence. 29 independent programmes arrived at the same structural conclusion without knowing about each other or the framework. This is not a claim of causation. It is an observation of convergence. The pattern holds across AI safety, quantum computing, classical physics, semiconductor manufacturing, Vatican doctrine, UN governance, venture capital, and mathematical logic. A pattern that appears in that many independent domains is not manufactured.

3. The proof IS independent of the researcher. Gumbau Mezquita's formal theorems do not depend on believing Eastwood. They do not depend on Eastwood's methods. They do not depend on Eastwood's sources. They are formal mathematical results - derived from Trakhtenbrot's Wall and Finite Model Theory, credited to Hernández-Espinosa, published two days ago on arXiv. They either hold or they don't. They hold. And they say what Eastwood said 18 months earlier.

4. Each link of the chain is independently verifiable. ND brain → manuscript → validations → protective-factor proof → formal vindication → clinical documentation → PNP framework → paper citing it all. Every link is independently verifiable. Every source is published. Every SHA-256 hash matches. The closed loop is not an argument. It is a chain of evidence.

4. Method

Convergences were identified through systematic search of 2025-2026 AI safety, quantum computing, hardware, semiconductor policy, Vatican doctrine, governance, neuroscience, and mathematics literature. Each convergence was tested against: (a) independent origin (no shared citations, personnel, or funding with Eastwood or with each other), (b) structural match (same principle, different substrate), and (c) temporal gap (date of Eastwood's articulation vs. date of independent confirmation). The Dec 8, 2024 manuscript was verified at line level against source files. All .eml files were SHA-256 verified. All external DOIs and arXiv IDs were confirmed.

5. Falsifiability

This claim is defeasible, and the criteria below state exactly what would defeat it. The strength of convergent evidence rests entirely on the convergences being genuinely independent, so these tests are adversarial by design.

1. Independence failure. Each convergence must arise from a source causally independent of the author's manuscripts and of every other convergence (see §4). The claim collapses to selection bias if a re-audit finds that a material fraction of the convergences share a common origin, cite one another, or were produced by parties with documented prior knowledge of the 8 December 2024 manuscript.
2. Defeat threshold (count). The count is itself a falsifiable claim. On a pre-registered re-audit applying strict one-event-per-row deduplication and primary-source verification, the pattern is defeated if the number of surviving independent convergences falls below the level distinguishable from chance co-occurrence given the breadth of domains searched. The nineteen claimed here are the verified rows only; candidates under verification are excluded from the count until sourced.
3. Missing denominator (disconfirming search). As evidence, the claim is defeated unless an equally systematic search for dis-confirming cases — domains where added recursive depth does not produce super-linear-above-threshold gains — is conducted and reported. Without the denominator (domains searched versus domains matching), the convergence rate cannot be shown to exceed chance.
4. Look-elsewhere effect. Across as many distinct domains as are surveyed here, some coincidental structural similarity is expected. The claim is defeated if the observed convergence rate does not exceed the false-positive rate expected from pattern-matching across that many independent domains.
5. Reverse causation. A convergence counts only if the external result was not, directly or indirectly, influenced by the author's own dissemination. Any convergence traceable to the book, the website, or public posts rather than pre-dating or arising independently of them is reclassified as engagement, not independent confirmation, and removed from the count.
6. Predictive failure. The structural principle makes forward predictions (that future recursive-depth results will show the same above-threshold super-linearity). Pre-registered predictions failing at a rate inconsistent with the claimed universality defeat the structural reading, leaving only a set of historical coincidences.

What would not defeat the claim: the reclassification of any single convergence, or one source proving weaker than described — the claim is about the aggregate pattern, not any individual row. But the aggregate must survive the independence, denominator, and base-rate tests above. Absent those, "convergent evidence" is indistinguishable from confirmation bias, and this paper says so plainly.

6. What This Means

For the ARC/Eden programme. The framework is not speculative. It has been independently corroborated nineteen times across nineteen domains. The corroboration is not from allies, collaborators, or people who know about the work; it is from people who do not know the work exists. Independent convergence of this breadth is strong corroborating evidence — but its weight depends entirely on the convergences being genuinely independent, which §5 sets out how to test.

For the researcher. The PNP framework describes the cognitive architecture that built this. The PNAS paper proved that architecture is protective. The formal proof vindicated the framework. The clinical documentation (Dr Woolley) provides the medical record. The closed loop is complete. The researcher's claim to expertise is not institutional. It is evidential. The evidence is published. The SHA-256 hashes match. The .eml files are downloadable.

For AI safety. nineteen independently sourced (plus candidates under verification) independent programmes have now confirmed that external alignment constraints are structurally insufficient - and that the solution involves embedding correction that co-scales with capability, at the substrate level, before the first decoupled recursive system ships. The convergent evidence now places the burden on sceptics to produce a counter-explanation. The question is whether any institution will act on it before the evidence becomes a post-mortem.

References

Declaration of AI-Assisted Human Authorship

The author of this work is Michael Darius Eastwood, a human being. Every core concept, hypothesis, experimental design, claim and conclusion in this paper originates from human ideation. No part of this manuscript is a wholly generated artificial-intelligence output.

Artificial-intelligence tools (Anthropic's Claude family and other large-language-model assistants) were used as instruments under continuous human direction, in the way a word processor, calculator or research assistant is used: for editing and prose refinement, literature search and summarisation (manually verified against primary sources), document structure, formatting, brainstorming against author-defined questions, and the acceleration of drafting to author-defined outlines and instructions. All selection, coordination, arrangement and final editorial judgment are the author's. Every substantive output was reviewed, tested or verified by the author, who takes full responsibility for the accuracy and integrity of the final text. The tools increased the speed of the work; they were never relied upon as its source.

United Kingdom. In accordance with the Copyright, Designs and Patents Act 1988, the author undertook the arrangements necessary for the creation of this work and asserts full human authorship and moral rights: this is a human-authored work produced with computer assistance, not a computer-generated work. United States. Consistent with United States Copyright Office guidance on works containing AI-generated material, the human contribution (conception, selection, coordination, arrangement and final expression) is asserted as sufficient for full human authorship. Inventions. Any novel technical contribution described in this work was conceived by the human author; no artificial-intelligence system autonomously invented anything presented here.