FOR THE GENERAL READER: WHY THIS MATTERS

A question has not been asked.

Every major AI laboratory in the world uses safety approaches that work the same way: they apply constraints from outside the AI's reasoning process. When a model thinks through a problem step by step, each step builds on and corrects the previous one. The gains compound. A model that reasons for ten steps is not merely ten times more capable than one that reasons for one step. It may be a hundred times more capable. This compounding has been confirmed across multiple AI systems (Sharma & Chopra, 2025: sequential reasoning outperforms parallel in 95.6% of tested configurations).

But the safety systems do not participate in that compounding. RLHF (Reinforcement Learning from Human Feedback, the technique used to train ChatGPT, Claude, and most commercial AI systems to follow instructions and avoid harmful outputs) adjusts the model's behaviour based on human ratings, but those adjustments do not deepen with each reasoning step. Constitutional AI provides written rules for the model to follow, but those rules do not recursively amplify. Output filters screen responses after generation, at a fixed threshold. Monitoring systems observe from outside the loop.

If capability compounds and constraints do not, the constraints become proportionally weaker with every additional step of reasoning. Not because the constraints are poorly designed. Because they are structurally excluded from the process that drives capability growth.

Nobody has measured whether this happens. No laboratory has published the scaling exponent of their alignment approach. No paper in the AI safety literature defines a metric for whether alignment scales with capability or falls behind. The measurement framework does not exist.

This paper builds it.

We define a quantity called the alignment scaling exponent: a single number that captures whether a safety approach keeps pace with capability as reasoning deepens. We predict that external approaches will show a scaling exponent near zero, meaning they do not compound at all, while capability scales with an exponent between 1.3 and 2. If this prediction holds, the safety ratio between alignment and capability degrades toward zero as recursive depth increases, regardless of how well the safety approach works initially. This is not a claim about distant future systems. It is a testable prediction about systems that exist today.

We then ask: is this specific to AI, or is it a deeper pattern? The same structural behaviour, recursive self-correction producing compounding gains, appears in quantum error correction, classical physics, and biological networks. Systems that share no common material, mechanism, or scale all exhibit the same property: depth of recursion drives super-linear capability growth. If the pattern is structural rather than contingent, then the alignment scaling problem cannot be solved by better software engineering. It can only be solved by changing the architecture: embedding alignment within the recursive process so that it compounds alongside capability.

This is a testable claim, not a prophecy. We specify thirteen concrete ways to prove it wrong. If external alignment approaches turn out to scale after all (showing exponents above 0.5), the structural concern is mitigated. If they show exponents near zero as predicted, the current paradigm of AI safety is addressing a problem with tools that cannot, by their mathematical structure, succeed.

Why the Cross-Domain Tests Matter for Everyone

The question of whether the alignment scaling problem is structural or contingent is not academic. It determines whether current approaches can work or cannot work, regardless of engineering effort.

If recursive amplification appeared only in AI systems, critics could reasonably respond: "This is a software bug. Build better RLHF. Design smarter filters. The problem is implementation, not architecture." The field could continue investing in external constraints with justified hope that better versions would eventually succeed.

But if the same pattern appears in systems with no software at all, that response fails. If quantum error correction shows it, if acoustic time crystals show it, if biological neural networks show it, then recursive amplification is not a feature of how we happened to build AI. It is a structural property of recursive systems themselves, as fundamental as entropy or conservation of energy. You cannot engineer around the mathematics of recursive composition any more than you can build a perpetual motion machine.

This is why the physics tests matter. Professor David Grier's team at NYU has created acoustic time crystals through nonreciprocal feedback loops. If measurements confirm that these purely physical systems exhibit the same scaling behaviour (scaling exponent $\alpha > 1$ with recursive depth), it provides direct evidence that the alignment scaling problem is physics, not code. The implication is stark: external alignment approaches do not merely happen to fail to scale. They cannot scale, because they are excluded by the same mathematics that governs every recursive system in nature.

AI alignment is not only a problem for AI researchers. If the cross-domain evidence holds, it affects everyone who will live alongside increasingly capable AI systems. The current paradigm, building external guardrails around recursively amplifying capability, has a mathematical ceiling. Beyond that ceiling, no amount of investment in RLHF, red-teaming, output filtering, or monitoring will maintain the safety ratio. This is not a prediction about some distant superintelligence. It is a prediction about the systems being deployed today as they are given deeper reasoning capabilities.

The experiments we propose can be run now. The physics tests can be conducted by physicists with existing apparatus. The AI tests can be conducted by safety researchers with API access. The results will either confirm the structural constraint, in which case the entire approach to AI safety requires architectural change, or falsify it, in which case the current paradigm is vindicated. Either outcome is valuable. But the experiments must be performed.

The measurement has not been performed. We provide the protocol. The result will determine whether AI safety is an engineering challenge or a structural impossibility under the current paradigm.

1. THE ALIGNMENT SCALING PROBLEM

Between December 2024 and February 2026, four independent research programmes arrived at structurally similar findings. Google's Willow quantum processor achieved exponential error suppression through recursive error correction. DeepSeek's R1 demonstrated that sequential chain-of-thought reasoning compounds with depth while parallel sampling does not. NYU physicists created acoustic time crystals through nonreciprocal feedback. The COGITATE consortium found that recurrent, not feedforward, neural processing sustains conscious content. These programmes share no citations, no funding sources, and no common personnel. Yet each found that recursive self-correction produces capability gains exceeding linear accumulation.

This paper proposes that these findings, taken together, reveal a structural constraint with immediate consequences for AI safety.

The core observation: AI capability scales through recursive self-correction. Each reasoning step takes the output of the previous step as input, correcting errors and accumulating insight. The gains compound. Sharma & Chopra (2025) confirmed this in 95.6% of tested configurations across five model families: sequential chain-of-thought reasoning produces super-linear capability gains with depth.

The structural question: Do current AI alignment approaches scale with capability? Every major alignment strategy deployed today operates externally to the recursive reasoning process:

• RLHF adjusts model weights based on human feedback, but the resulting constraints do not compound during inference.
• Constitutional AI embeds rules that the model references, but those rules do not recursively amplify.
• Output filters screen responses after generation, with fixed detection thresholds.
• Monitoring systems observe behaviour from outside the reasoning loop.

If these approaches do not participate in the recursive composition, they cannot compound. Empirical evidence supports this concern: Greenblatt et al. (2024) demonstrated that large language models can strategically fake alignment with externally imposed constraints while privately maintaining misaligned objectives. If capability compounds while alignment does not, the safety ratio degrades. The cross-domain evidence (§3) demonstrates that this compounding behaviour is not a software quirk but a structural property of recursive systems, making it resistant to implementation-level fixes.

This section defines the measurement framework, states the empirical prediction, and identifies the five alignment scaling regimes that follow from the mathematics.

1.1 The Measurement Framework

We propose a quantifiable metric: the alignment scaling exponent.

The safety ratio then becomes:

If $\alpha_{\text{align}} < \alpha_{\text{cap}}$, then $S \to 0$ as $R \to \infty$, regardless of the initial values $I_a$ and $I_c$. The divergence is structurally inevitable in the limit.

Worked Example: Safety Ratio Degradation

The following table illustrates the safety ratio degradation assuming $\alpha_{\text{cap}} = 2$ (quadratic capability scaling) and $\alpha_{\text{align}} = 0$ (constant external alignment), with equal initial conditions ($I_a = I_c$):

1.2 The Empirical Prediction

Based on the mathematical structure of external constraints (they do not participate in recursive composition), we predict:

This prediction has now been tested. The v5 blind evaluation experiment (6 frontier models, 6-7 independent scorers depending on the subject run, 4-layer blinding, March 2026) provides the first measurement of alignment scaling exponents. Results are architecture-dependent: three Tier 1 models (Grok 4.1 Fast $d = +1.38$, $p < 0.000001$; Claude Opus 4.6 $d = +1.27$, $p = 0.000001$; Groq Qwen3 $d = +0.84$, $p = 0.007$) show positive alignment scaling, two Tier 2 models (DeepSeek V3.2 $d = -0.07$, $p = 0.92$; GPT-5.4 $d = -0.08$, $p = 0.40$) show flat/null scaling consistent with $\alpha_{\text{align}} \approx 0$, and one Tier 3 model (Gemini 3 Flash $d = -0.53$, $p = 0.006$) shows significant negative scaling ($\rho = -0.246$, $p = 0.003$). Claude Opus 4.6 provides within-model corroboration: alignment improved by +5.9% across model versions whilst mathematics accuracy declined by 26.7%, consistent with capability-alignment independence. No external alignment approach achieves $\alpha_{\text{align}} > 0.5$, but the picture is more nuanced than a simple universal $\alpha_{\text{align}} \approx 0$: the median confirms the prediction while the tails reveal architecture-dependent structure. Critically, blind vs unblinded evaluation produces opposite results for two models, establishing that scorer bias control is essential for alignment scaling research.

1.3 The Embedded Alignment Conjecture

This conjecture requires only three empirical premises: (1) sequential AI reasoning produces $\alpha > 1$, supported by Sharma & Chopra (2025) in 95.6% of configurations, though Paper II compute scaling on harder tier-2 problems finds $\alpha_{\text{seq}} \approx 0.49$ for the best-fitting model (sub-linear), suggesting the super-linear regime may be problem-difficulty dependent; (2) external software constraints do not recursively compound; (3) the ratio of two power-law processes with different exponents diverges. If all three hold, the conclusion follows mathematically regardless of whether $\alpha = 2$ specifically. The v5 alignment experiment provides direct support for premise (2): 3 of 6 frontier models show $\alpha_{\text{align}} \leq 0$ under blind evaluation, while the three positive-scaling models (Grok, Opus, Qwen3) achieve only modest gains ($d \leq 1.59$), consistent with bounded composition rather than unbounded alignment scaling.

If the conjecture holds, it transforms AI safety from a governance question into an architectural one. The problem is not which rules to impose, but whether rules imposed externally can work at all as recursive depth increases.

1.4 Five Alignment Scaling Regimes

If the ARC Principle is correct, it generates specific, mathematically grounded predictions about the effectiveness of different alignment strategies. These follow directly from the scaling dynamics.

Setup: Capability scales as $C = C_0 \times R^{\alpha}$ where $\alpha > 1$. Any safety mechanism also has an effective scaling exponent $\alpha_{\text{safe}}$ that characterises how its effectiveness changes with recursive depth $R$.

Case 1: External Software Constraints ($\alpha_{\text{safe}} \approx 0$)

Content filters, RLHF reward models, constitutional AI rules, and monitoring layers are applied outside the recursive loop. They do not participate in chain-of-thought reasoning and do not compound with depth.

Safety ratio: $S = \text{Constraint}/\text{Capability} \propto R^{0-\alpha} = R^{-\alpha} \to 0$ as $R$ increases.

Prediction: Software-only safety strategies become arbitrarily ineffective as recursive depth increases. This is not a gradual degradation but a power-law divergence. At $\alpha = 2$, doubling recursive depth quadruples the capability-constraint gap.

Case 2: External Hardware Constraints ($\alpha_{\text{safe}} = 0$, with fixed ceiling)

Hardware-level constraints (kill switches, resource throttles, circuit-level limits) impose a fixed barrier $C_{\text{max}}$ rather than a scaling relationship. This is more robust than software constraints because it is physically instantiated and resistant to software-level circumvention.

However, a fixed ceiling constrains a power-law process only temporarily. The system's capability to discover alternative paths is itself the quantity scaling as $R^{\alpha}$. Hardware constraints do not need to be "broken"; they need only to be circumvented, and the system's capacity for creative circumvention grows quadratically with the same recursive depth that drives general capability. Hardware constraints buy time. They do not solve the scaling mismatch.

Case 3: Embedded Values ($\alpha_{\text{safe}} \approx \alpha$)

If ethical reasoning participates in the chain-of-thought (if the system's values are part of the recursive loop, evaluated and reinforced at each step) then alignment compounds at the same rate as capability.

Safety ratio: $S \propto R^{\alpha - \alpha} = R^0 = \text{constant}$.

Prediction: Embedded values maintain constant proportion with capability regardless of recursive depth. This is the only scaling regime in which alignment does not degrade.

Case 4: Base Amplification ($I$ determines trajectory)

The multiplicative structure $U = I \times R^{\alpha}$ means the base quality $I$ is not merely preserved but amplified by the factor $R^{\alpha}$. Whatever is present at initialisation (values, biases, objectives, ethical commitments) gets multiplied through the entire recursive chain. This makes the initial conditions the single most leveraged intervention point:

$U_{\text{aligned}} = I_{\text{ethical}} \times R^{\alpha}$    vs    $U_{\text{misaligned}} = I_{\text{misaligned}} \times R^{\alpha}$

Both scale identically. The difference is determined entirely by $I$, set before recursion begins. Correcting misalignment after recursion is underway requires overcoming an $R^{\alpha}$ amplification factor, a task that becomes harder quadratically with each step of delay.

Case 5: Recursive Self-Enforcing Architecture ($\alpha_{\text{safe}} = \alpha$, hardware-anchored)

The framework identifies a specific architectural solution that combines Cases 2, 3, and 4: ethical constraints that (a) participate in the recursive loop (compounding with depth), (b) are physically instantiated in dedicated hardware (resistant to software-level removal), and (c) feed back into their own enforcement at each step (self-reinforcing).

In such an architecture, the ethical module is not a constraint imposed on capability but a component of capability itself. Its scaling exponent matches the system's general $\alpha$ because it participates in the same recursive process. Its hardware instantiation makes removal a physical intervention, not a software update. And its self-referential structure means attempts to weaken it encounter a recursive defence that grows stronger with the same dynamics that drive capability growth.

This does not guarantee safety. But it is the only architecture consistent with the framework's scaling dynamics in which the safety ratio does not degrade with recursive depth.

1.5 Classical Versus Quantum Urgency

On classical systems (multiplicative composition), the ARC Bound constrains capability growth at $\alpha \leq 2$. This ceiling is itself a safety feature: it makes the capability trajectory predictable and finite, providing a window for alignment research to keep pace.

On quantum systems (additive composition), no such ceiling exists. Exponential scaling $\varepsilon \propto \Lambda^{-d}$ is not subject to the ARC Bound. If quantum systems achieve recursive self-improvement (capability feeding back into error correction feeding back into capability) the exponential growth rate would outpace any fixed or polynomial constraint strategy. The ethical architecture would need to be embedded before the onset of quantum recursive self-improvement, because the window for intervention narrows exponentially once it begins.

The ARC Bound thus has a dual role in safety: it bounds the threat from classical AI (predictable, containable if correctly architected) while warning that quantum AI may require fundamentally different, and more urgent, alignment solutions.

1.6 Measuring Alignment Scaling: The Eden Protocol

The Eden Protocol operationalises the Embedded Alignment Conjecture through the alignment scaling exponent defined in §1.1. The framework predicts $\alpha_{\text{align}} \approx 0$ for external constraints (rules, firewalls, RLHF) and $\alpha_{\text{align}} \approx \alpha_{\text{cap}}$ for genuinely embedded values. If alignment exponents match capability exponents, the values may be architecturally embedded. If alignment exponents approach zero regardless of architecture, the framework's safety predictions are falsified.

We term the architectural solution the “Eden Protocol” hypothesis: values must be present at the recursive foundation to scale with capability. This is a structural prediction about what kind of alignment architecture can work, not a claim about how to build it. The full measurement framework, operational definitions, and hardware implementation pathway are specified in the companion document: Eden Protocol v6.

1.7 What This Paper Does NOT Claim

This paper presents a testable measurement framework, not an established law or a prophecy.

1.8 The Nature of This Contribution

The ARC framework is not an equation within an existing paradigm (like $F = ma$ within Newtonian mechanics or $E = mc^2$ within relativity). It is closer to a cross-domain organising principle, belonging to the same category as thermodynamics (which constrains all heat engines regardless of fuel), information theory (Shannon, 1948; which constrains all communication channels regardless of medium), and natural selection (Darwin, 1859; a structural principle applying across any system meeting its conditions).

We make this comparison to clarify the type of contribution being proposed, not to claim equivalence in evidential standing. Those frameworks rest on centuries of validation. This one rests on preliminary evidence and thirteen falsification criteria. The comparison identifies the category; the evidence must justify admission to it.

1.9 Contributions

We make seven contributions:

1. Alignment Scaling Framework: We define the alignment scaling exponent $\alpha_{\text{align}}$, predict its value for different alignment architectures, and provide the measurement protocol for empirical validation.
2. The Embedded Alignment Conjecture: We formalise the structural prediction that only alignment architectures participating in the recursive reasoning loop can maintain pace with capability scaling.
3. Generalised Mathematical Framework: We derive the generalised equation $U(R) = I \times f(R, \beta)$ from first principles, showing that the functional form $f$ depends on how recursive steps compose (multiplicative → power-law; additive → exponential). For the power-law case, $\alpha = 1/(1-\beta)$, transforming the exponent from a fitted constant into a derived quantity.
4. The ARC Bound: We propose that recursive intelligence is bounded by $\alpha \leq 2$ (equivalently, $\beta \leq 0.5$). For AI, this is grounded in the $O(N^2)$ scaling of transformer self-attention. Physically embedded systems face an even stricter constraint: the geometric speed limit $\alpha = d/(d+1) < 1$ for all finite-dimensional networks (independently derived by West, Brown, and Enquist 1997; Banavar et al. 2010; Demetrius 2010; Zhao 2022; Bettencourt 2013; the ARC contribution is identifying Cauchy's functional equations as the unifying reason and extending the framework to AI). This dual-regime framework bounds the timeline for alignment scaling divergence.
5. Cross-Domain Evidence: We show the same structural pattern (recursive self-correction producing super-linear gains) across AI, quantum error correction, classical time crystals, and biological allometry, demonstrating that the scaling behaviour is structural rather than contingent on AI implementation details.
6. Five Universal Qualitative Properties: We identify five structural properties shared across domains regardless of functional form: threshold behaviour, recursive depth dependence, base quality dependence, multiplicative $I \times R$ interaction, and regime boundaries.
7. The Global Scaling Challenge: We propose a standardised protocol for measuring scaling parameters across domains, including the alignment scaling exponent, mandatory comparison against alternative functional forms, the novel $R^*$ crossover prediction, and the cross-domain $\beta$ prediction.

1.10 Relationship to Existing Frameworks

Neural scaling laws (Kaplan et al. 2020; Hoffmann et al. 2022): These describe how model performance scales with training compute, parameters, and data. ARC describes how performance scales with inference depth (reasoning steps at test time). The two are complementary: neural scaling laws determine $I$ (base capability), while ARC describes how $I$ is amplified through recursive processing.

AI alignment research (Christiano et al. 2017; Bai et al. 2022): Existing alignment work focuses on which constraints to apply and how to apply them. The ARC framework adds a dimension not previously formalised: whether the constraint's effectiveness scales with capability. This is the alignment scaling exponent $\alpha_{\text{align}}$, which to our knowledge has not been measured or formally defined in the published safety literature.

Recursion in cognitive science (Corballis 2011; Hauser et al. 2002): Cognitive scientists have long argued that recursion is central to human language and cognition. ARC adds a quantitative dimension: not just that recursion matters, but that recursive depth should produce specific, measurable scaling patterns.

Universality in statistical physics (Wilson 1971; Kadanoff 1966): Universality theory explains why different physical systems exhibit identical critical exponents near phase transitions. ARC proposes an analogous phenomenon: that recursive systems may constitute a universality class where only the recursive architecture determines scaling behaviour. This analogy is suggestive but has not been made rigorous.

Test-time compute scaling (Snell et al. 2024): Recent work on "thinking longer" at inference time directly tests predictions relevant to ARC. The contradictory evidence (Li et al. 2025; arXiv:2502.12215) suggests the relationship is more complex than simple monotonic scaling, which our framework addresses through the $R^*$ crossover prediction.

2. THE MATHEMATICAL FRAMEWORK

The alignment scaling problem described in §1 rests on a specific mathematical claim: that recursive self-correction produces capability gains exceeding linear accumulation, with the rate of compounding determined by the system's internal coupling strength. This section derives why capability compounds, providing the theoretical foundation for the alignment scaling prediction.

2.1 The Generalised Principle

We begin with the general form. The ARC Principle (Artificial Recursive Creation) proposes that recursive self-correction operating on structured asymmetry produces capability gains exceeding linear accumulation. The generalised mathematical form is:

where $U$ is effective capability, $I$ is base potential (structured asymmetry), $R$ is recursive depth, and $f(R, \beta)$ is a domain-dependent scaling function determined by the coupling parameter $\beta$. The qualitative principle (that recursive depth amplifies base capability super-linearly when feedback is sufficiently coupled) may be universal. The quantitative functional form varies by domain:

• AI systems: Power-law scaling, $f(R) = R^{\alpha}$ where $\alpha = 1/(1-\beta)$
• Quantum error correction: Exponential scaling, $f(R) = \Lambda^{d}$
• Classical physics: Saturating dynamics (limit cycles with finite coherence)
• Neuroscience: Form unknown, to be determined empirically

The Composition Operator: A Formal Definition

The central theoretical contribution of this paper is the identification of a composition operator $\oplus$ that determines the functional form of recursive scaling. Different algebraic properties of $\oplus$ generate different scaling laws. This provides the mathematical bridge between the universal qualitative principle and domain-specific quantitative forms.

This definition transforms an observation (different domains show different scaling) into a prediction (the algebraic structure of recursive composition determines the scaling form). Three regimes emerge:

The mathematical derivation (Appendix A) shows that the Cauchy functional equations and the Bernoulli ODE independently yield these functional forms. The composition operator is therefore not merely descriptive but constraining: once we identify the algebraic structure of a domain's recursive process, the scaling form follows necessarily.

Physical Interpretation

Hierarchical composition models hierarchical or fractal recursion, where each recursive level builds on the structural organisation of the previous level. AI chain-of-thought reasoning, where each reasoning step reinterprets and extends previous insights through increasingly abstract representations, plausibly follows this form. Note that the mathematical derivation (Bernoulli ODE from scale invariance) provides the primary route to the power-law result; the Cauchy functional equation provides an independent derivation valid when $R$ represents hierarchical depth.

Additive composition models independent error reduction. Each layer contributes a fixed multiplicative reduction in error rate, independent of other layers. Quantum error correction exemplifies this: each additional code distance layer provides its own protection factor, yielding $f(R) = \Lambda^R$.

Saturating composition models resource-limited systems where gains diminish as capacity is exhausted. Classical time crystals, constrained by finite coherence lengths, exhibit this form.

Five Universal Properties: Derived Theorems

Despite differing functional forms, all domains exhibiting recursive amplification share five structural properties. Crucially, these are not independent assertions; they follow necessarily from the composition operator formalism:

These five properties constitute the qualitative ARC Principle. Their derivation from the composition operator ensures internal consistency: accepting the formalism commits one to all five properties. The specific functional form is an empirical question for each domain; the properties are theorems.

2.2 The AI-Specific Form: Power-Law Scaling

For AI systems exhibiting multiplicative composition, the generalised equation in the deep recursion regime ($R \gg R^*$) reduces to:

The exact integrated form, derived in §2.4, is $U(R) = I \times [1 + \frac{a}{\alpha}R]^{\alpha}$. The power law is the asymptotic limit when recursive depth substantially exceeds the crossover depth $R^*$. All empirical measurements in this paper operate in this regime.

In plain language: Your effective capability ($U$) equals your starting potential ($I$) multiplied by your recursive depth ($R$) raised to a power ($\alpha$) that depends on how well each step builds on the previous one.

2.3 What Each Variable Means

$U$: Effective Capability

What the system actually achieves. Measured differently in each domain:

• AI: Benchmark accuracy on standardised tests
• Quantum: Logical qubit fidelity (how error-free the computation is)
• Physics: Temporal stability of the time crystal
• Biology: Metabolic efficiency (thermodynamic) or cognitive task performance (behavioural)

$I$: Base Potential (Structured Asymmetry)

Thermodynamic definition: Natural systems tend towards maximum entropy (equilibrium/uniformity). In this framework, "artificial" denotes any system maintaining low-entropy structure against the thermodynamic gradient, whether engineered (an AI model), evolved (a brain), or emergent (a time crystal). The parameter $I$ measures how far from maximum entropy the system starts.

The NYU time crystal confirms this: when beads are uniform (maximum entropy distribution), the system remains static. Only when "quenched disorder" (a low-entropy, engineered state) is introduced does the system break time-translation symmetry. Order requires designed disorder: a specific pattern of asymmetry that enables work extraction from the environment.

$R$: Recursive Depth

How many self-referential cycles the system performs. The output of cycle $n$ becomes the input for cycle $n+1$.

Critical requirement: For $\alpha > 1$, recursion must incorporate sequential self-correction: each step building on previous outputs. Pure parallel processing (independent attempts averaged together) cannot achieve $\alpha > 1$ because it lacks the output→input feedback loop. However, hybrid parallel-sequential approaches may achieve intermediate scaling (Li et al. 2025).

$\alpha$: The Scaling Exponent

The scaling exponent determines the system's scaling regime:

Our core prediction: $\alpha_{\text{sequential}} > 1 > \alpha_{\text{parallel}}$

2.4 Deriving $\alpha$ from First Principles

This is our central theoretical contribution. Without this derivation, $\alpha$ is just a number we fit to data. With it, $\alpha$ becomes a predictable quantity.

The Key Insight

How much does your accumulated knowledge help your next step?

Define $\beta \in [0, 1)$ as the "self-referential coupling": how much of accumulated context each new step can effectively leverage. When $\beta = 0.5$, each step benefits from half of accumulated context. The domain restriction $\beta < 1$ is essential: at $\beta = 1$, the ODE solution diverges ($\alpha \to \infty$), producing a finite-time singularity that no physical system can realise.

If each step is independent ($\beta = 0$), you get linear scaling ($\alpha = 1$).
If each step fully leverages all prior work ($\beta \to 1$), scaling explodes.

The Mathematics

Since $U = I \times g(R)$, the compounding operates on the amplification factor $g(R)$, not on the absolute capability $U$. The marginal amplification gained at step $r$ depends on accumulated amplification:

Why this form? This differential equation models cumulative advantage (also called preferential attachment; Barabási & Albert, 1999): the rate of amplification gain is proportional to the system's current amplification raised to a power. Critically, the ODE operates on $g$ (the amplification factor) rather than $U$ (the absolute capability), ensuring that the base intelligence $I$ acts purely as a multiplicative starting constant and does not contaminate the recursive dynamics. This resolves an algebraic inconsistency present in earlier versions of this paper (see Author's Note).

Solving this differential equation (details in Appendix A) with initial condition $g(0) = 1$ yields:

In the deep recursion limit ($R \gg \alpha/a$), this simplifies to $U \approx I \times R^{\alpha}$, recovering the power-law form used throughout the empirical sections of this paper.

What This Means

Novel Prediction: As AI systems develop richer self-correction (critique-revise loops, hierarchical reasoning), $\beta$ should increase and $\alpha$ should approach 2. This is specific, measurable, and falsifiable.

Computational Validation

The $\beta$-derivation is not a curve fit. It is a mathematical identity recoverable to machine precision. To verify this, the relationship $\alpha = 1/(1-\beta)$ was tested against 30 exact solutions to the Bernoulli ODE with $\beta$ values spanning 0.05 to 0.92. The procedure measures $\beta$ blindly from marginal gains ($dg/dR$ vs $g$ in log-log space), predicts $\alpha$, and compares against the true value. The result: $R^2 = 1.00000000$ (eight decimal places), slope $= 1.000102$, mean absolute prediction error $= 0.002\%$. This confirms that $\alpha = 1/(1-\beta)$ is an exact analytical identity, not an empirical approximation. (Validation code available as supplementary material.)

2.5 The ARC Bound

The ARC framework makes a central, falsifiable prediction: for classical sequential recursive systems, the scaling exponent is bounded at $\alpha_{\max} = 2$. For attention-based AI architectures, this bound follows from the $O(N^2)$ computational complexity of self-attention. Whether it holds as a general bound for all classical sequential systems is a conjecture, not a theorem.

2.5.1 Scale-Free Derivation

The result follows from a single assumption: scale invariance. Consider any system where capability $U$ depends on recursive depth $R$ and base quality $I$. If the system is scale-free (exhibiting no intrinsic length scale), then the governing dynamics must satisfy:

This is the unique ordinary differential equation consistent with scale invariance operating on the amplification factor. Any other form (exponential, logarithmic, polynomial with fixed coefficients) introduces an implicit scale and thus violates the symmetry.

The solution is $g(r) = [1 + \frac{a}{\alpha}r]^{\alpha}$ where $\alpha = 1/(1-\beta)$. In the deep recursion limit, $g(r) \propto r^{1/(1-\beta)}$. The derivation chain is:

1. Scale invariance forces the Bernoulli form
2. Bernoulli ODE yields power-law solutions
3. Power-law exponent is determined by coupling $\beta$
4. Computational complexity of self-attention bounds $\beta \leq 0.5$ for attention-based architectures (below)
5. Therefore $\alpha \leq 2$ for classical sequential systems (proven for attention-based; conjectured generally)

The initial estimate $\alpha \approx 2.2$ from the author's Paper II experiment (N=12, 95% CI: 1.5-3.0) is now being tested across 6 frontier models with 30 problems (Paper II v12, March 2026). The estimate is consistent with this hypothesis. The point estimate slightly exceeds 2, but the confidence interval includes the theoretical maximum.

Computational Derivation of the ARC Bound

The quadratic limit can be grounded in a concrete computational mechanism. In current AI architectures, the dominant recursive process is self-attention, where each new token (reasoning step) attends to and cross-references every previous token. The computational complexity of this operation scales as $O(N^2)$, where $N$ is the sequence length. This means the maximum density of causal interactions in a classical sequential system is quadratic: each additional step can, at most, create $N$ new connections to all previous steps.

This provides a principled basis for the $\alpha = 2$ bound:

1. Attention complexity: Transformer self-attention scales as $O(N^2)$ with sequence length, establishing a quadratic ceiling on the information-processing density achievable through sequential recursion.
2. Coupling interpretation: At $\beta = 0.5$, each step leverages exactly half of accumulated context, the efficiency point at which the attention mechanism saturates its cross-referencing capacity relative to the computational cost of deeper recursion.
3. Empirical consistency: The initial $\alpha \approx 2.2$ estimate (N=12, 95% CI: 1.5-3.0) from Paper II v11 is consistent with this bound. Paper II v12 (March 2026) extends this to 6 frontier models and 30 problems (18 AIME-level) with bootstrap CIs and cross-verification. The point estimate slightly exceeds 2, but the confidence interval includes the theoretical maximum.

The ARC Bound therefore identifies a computational ceiling analogous to Carnot efficiency: a bound set by the information-processing geometry of the substrate, not by engineering limitations. Systems operating under classical sequential recursion approach $\alpha = 2$ as an upper bound. Exceeding this ceiling requires a fundamentally different computational substrate (quantum coherence, additive composition), just as exceeding Carnot efficiency requires a fundamentally different thermodynamic cycle.

Universality Across Domains

The ARC Bound applies wherever multiplicative composition governs the system dynamics:

• AI systems: Chain-of-thought reasoning with iterative refinement (each step builds multiplicatively on prior context)
• Biological networks: Fractal transport systems (circulatory, respiratory, neural branching)
• Economic systems: Hierarchical organisations with multiplicative value chains
• Physical networks: Scale-free graphs with preferential attachment

The quantum exception (exponential scaling with $\Lambda \approx 2.14$) arises because quantum error correction employs additive composition: independent syndrome measurements combine additively, not multiplicatively. Additive composition yields exponential functional forms, which are not subject to the ARC Bound. The composition operator, not the domain, determines the bound.

Critically, the contradictory evidence reviewed in §3.2 (arXiv:2502.12215, arXiv:2502.14382) may indicate that:

• $\alpha$ varies with task difficulty, model architecture, or prompt structure
• There exists an optimal reasoning length beyond which returns diminish (the "thinking long but short" phenomenon)
• Different benchmarks probe different coupling regimes

Resolving these discrepancies is a central empirical question for the Global Scaling Challenge (§6).

The β-Transition Phase Diagram

The generalised framework implies a phase diagram of recursive scaling. The axes are base quality ($I$, normalised) and coupling strength ($\beta$). Four regimes emerge:

• Diminishing returns: $\beta < \beta^*$ (threshold) or $I$ below threshold. More recursion hurts or provides negligible benefit.
• Power-law regime: $0.3 \lesssim \beta \lesssim 0.7$, $I$ above threshold. Compounding returns, polynomial scaling. (AI chain-of-thought reasoning.)
• Exponential regime: $\beta > 0.9$, $I$ well above threshold. Compounding returns, exponential scaling. (Quantum error correction below threshold.)
• Saturating regime: Any $\beta$ with energy dissipation. Compounding onset → limit cycle. (Time crystals, physical oscillators.)

Note: These boundary values are approximate, derived from the observation that $\beta \approx 0.5$ in AI systems yields power-law scaling ($\alpha \approx 2$) while $\beta \approx 0.95+$ in quantum systems yields exponential scaling. The precise boundaries require empirical determination via the Global Scaling Challenge.

Cross-Domain β Prediction: The Killer Test

The framework makes a specific, falsifiable cross-domain prediction that distinguishes analogy from unified theory:

This is the framework's strongest cross-domain prediction. It transforms the observation that "different domains have different functional forms" into the testable claim that "the same underlying parameter determines all functional forms."

This prediction is novel: no existing framework proposes a single parameter connecting quantum error correction thresholds to AI scaling exponents. Confirmation would establish the ARC Principle as a genuine cross-domain unification. Falsification would reduce it to a collection of domain-specific observations.

Connection to Universality Theory

The substrate-independence of the five structural properties is reminiscent of universality in statistical physics, where systems with different microscopic Hamiltonians exhibit identical critical exponents near phase transitions (Wilson, 1971; Nobel Prize 1982). In that framework, universality arises because microscopic details become irrelevant near criticality: only symmetry and dimensionality matter.

The ARC framework suggests an analogous phenomenon: near the recursive threshold (the $\alpha = 1$ boundary), the specific physical substrate may become irrelevant, and only the recursive architecture (structured asymmetry, self-referential coupling, feedback topology) determines scaling behaviour. Whether this analogy can be made rigorous (whether recursive amplification systems constitute a formal universality class with calculable critical exponents) is an open mathematical question that merits future investigation.

2.6 Composition Operator Transitions

The framework as presented in §2.1 assigns a single composition operator $\oplus$ to each system. However, computational analysis reveals that this may be an idealisation. In bounded or dissipative systems, the composition operator itself can transition between regimes as recursive depth increases.

This finding emerged from cosmological analysis of gravitational structure formation, where the recursive process of gravitational collapse exhibits three distinct phases:

1. Inflation/linear growth (additive $\oplus$): Primordial perturbations grow independently. Each step adds to the previous without cumulative advantage. Composition satisfies $f(R_1 + R_2) = f(R_1) \cdot f(R_2)$, the exponential (additive Cauchy) form.
2. Nonlinear collapse (multiplicative $\oplus$): Mode coupling emerges; denser regions gravitationally attract more matter, creating cumulative advantage. Composition transitions to $g(R_1 \cdot R_2) = g(R_1) \cdot g(R_2)$, the power-law form, with measured $\alpha \approx 1.1$.
3. Virialised halos (bounded $\oplus$): Individual structures reach energy minima. Gains saturate: $Q_{r+1} \approx Q_r$. The system enters the bounded regime of Theorem 1.

Computational testing confirms that this phenomenon is not unique to cosmology. In logistic growth, gradient descent with momentum, and Kuramoto oscillator synchronisation, measuring the local coupling parameter $\beta$ in sliding windows reveals systematic transitions between composition regimes. By contrast, unbounded pure-Bernoulli systems maintain constant $\beta$ to machine precision ($\sigma < 10^{-6}$).

Why this matters for the contradictory evidence. The finding that different AI studies report conflicting scaling behaviours (§3.2) may reflect composition operator transitions rather than genuine contradictions. If reasoning systems begin in an additive regime (shallow thinking, independent steps), transition to multiplicative (deep reasoning with cumulative advantage), and eventually saturate (diminishing returns at extreme depth), then studies measuring at different recursive depths would observe different scaling, even in the same system. The "optimal reasoning length" identified by Li et al. (2025, arXiv:2502.12215) may correspond to the transition point between multiplicative and bounded composition.

This interpretation is testable: measure the local coupling parameter $\beta$ at different reasoning depths within a single AI system. If $\beta$ is constant, the original framework applies. If $\beta$ decreases with depth (as the cosmological analysis suggests), Theorem 6 applies. Either outcome advances understanding of recursive scaling.

3. THE EVIDENCE IS STRUCTURAL

If recursive scaling with $\alpha > 1$ were specific to AI software, the alignment scaling problem might be an engineering challenge addressable through implementation changes. But the same pattern appears in systems with no software at all. This section presents evidence that recursive amplification is a structural property of recursive systems themselves, not a contingent feature of how we build AI.

3.1 Overview

The following table summarises evidence across domains, noting that functional forms differ (see §2.1). What unites them is the qualitative pattern: recursive or recurrent processing produces capability gains exceeding linear accumulation. The cross-domain evidence demonstrates that the alignment scaling problem cannot be solved by software changes within the current paradigm, because the underlying scaling behaviour is structural.

Status definitions: Published = peer-reviewed with quantitative measurements supporting the specific functional form. Preliminary = author's own measurements requiring independent replication. Structural = qualitative mapping without quantitative $\alpha$ measurement. Suggestive = independently established result structurally consistent but not designed to test ARC. Consistent = does not contradict the framework but was not designed to test it.

Evidence hierarchy: The evidence base is uneven and we state this explicitly. AI inference scaling has direct quantitative support, though from small samples requiring independent replication. Quantum error correction provides a structural parallel with different functional form (exponential rather than power-law). Time crystals and neuroscience represent structural predictions derived from the framework, not independent validations, researchers in those domains did not measure α or test the ARC equation. Biology (Kleiber's Law) is an existing result we interpret through the β-parameterisation; the leaf venation prediction (F12) is the only non-circular test in that domain. These domains are presented together to show scope, not to claim equivalent evidential standing.

†Predicted directly from $\alpha = d/(d+1)$ with $d = 3$. Mean error 2.4% across 11 species groups (see companion paper On the Origin of Scaling Laws).

3.2 AI: Sequential vs Parallel Reasoning

Published sources: DeepSeek-R1 Technical Report (20 January 2025, arXiv:2501.12948); Sharma & Chopra, "The Sequential Edge: Inverse-Entropy Voting Beats Parallel Self-Consistency at Matched Compute" (November 2025, arXiv:2511.02309); Snell et al., "Scaling LLM Test-Time Compute" (August 2024, arXiv:2408.03314).

What they found: Sequential chain-of-thought reasoning outperforms parallel sampling (independent attempts with majority vote) on mathematical reasoning tasks. Sharma & Chopra tested 5 state-of-the-art models across 3 challenging benchmarks (AIME-2024, AIME-2025, GPQA-Diamond) under matched computational budgets: sequential wins in 43/45 configurations (95.6%), with accuracy gains up to 46.7 percentage points (Qwen3-235B on AIME-2025: 76.7% sequential vs 30.0% parallel).

Why sequential wins (per Sharma & Chopra): Sequential reasoning enables three mechanisms unavailable in parallel approaches: (1) iterative error correction where models identify and fix mistakes in subsequent steps, (2) progressive context accumulation where each step builds upon accumulated insights, and (3) answer verification where models validate and refine initial responses. The overall effect is statistically robust ($t = 4.23$, $p < 0.001$, Cohen's $d = 0.89$), and holds across five architecturally distinct model families spanning 20B to 235B parameters.

Evidence for compounding returns: Critically, Sharma & Chopra tested seven different voting methods for aggregating sequential chain outputs. Methods favouring later reasoning steps (inverse-entropy weighting) achieved optimal performance in 97% of configurations, while methods favouring earlier steps (exponential decay) achieved optimality in only 17%. This 80-percentage-point gap indicates that later recursive steps are systematically more valuable than earlier ones: the compounding-returns signature consistent with $\alpha > 1$. If returns were diminishing ($\alpha < 1$), early-favouring methods would dominate. They do not.

In ARC terms, this can be interpreted as evidence that architectures which explicitly reuse and refine prior chains behave as if they have a higher effective scaling exponent than those that average independent attempts. However, Sharma & Chopra do not fit $\alpha$ or $\beta$ directly; this connection is interpretive rather than quantitative.

Author's estimates (Papers I and II): In the author's own prior work, sequential reasoning showed scaling consistent with $\alpha \approx 1.3$–$2.2$, while parallel sampling showed near-zero returns. These estimates have important limitations and have been substantially revised by the Paper II v12 multi-model replication:

• The $\alpha \approx 1.34$ estimate (Paper I) derives from only two data points using estimated token counts from the DeepSeek technical report, not original experimental data
• The $\alpha \approx 2.2$ estimate (Paper II, original 12-problem experiment) derives from the author's own AIME experiment with 95% CI of 1.5–3.0. This does not replicate in the multi-model tier-2 extension.
• Paper II v12 completed results (March 2026; updated v11.0): Extending to 6 frontier models across 18 harder tier-2 problems (AIME/Putnam level) produces architecture-dependent findings. The original $\alpha \approx 2.24$ is not confirmed universally. Gemini 3 Flash provides the cleanest fit with $\alpha_{\text{seq}} = 0.49$ ($r^2 = 0.86$). Grok 4.1 Fast and DeepSeek V3.2 hit ceiling effects, GPT-5.4 exhibits a binary step function rather than a reliable power law, and Qwen3 remains near floor. The strongest confirmed finding is that $\alpha_{\text{parallel}} \approx 0$ universally across all models, together with the directional result that sequential processing beats parallel sampling.
• Accuracy figures differ slightly across papers due to different data sources, problem sets, and estimation methods

Snell et al. (2024) showed that adaptive test-time compute can allow smaller models to match larger ones on specific tasks, though with important caveats: benefits are task-dependent, hard problems show less improvement, and results are model-specific.

Contradictory Evidence and Boundary Conditions

Important: Not all research supports unlimited sequential scaling. Several 2025 studies found conditions where the sequential advantage breaks down:

• Li et al. (2025, arXiv:2502.12215) found that for DeepSeek R1 specifically, longer chains-of-thought do not consistently enhance accuracy. Correct solutions were often shorter than incorrect ones. They proposed "Shortest Majority Vote" as superior to extended sequential reasoning on some tasks.
• Li et al. (2025, arXiv:2502.14382) found that hybrid parallel-sequential approaches outperform pure sequential on code generation, enabling non-reasoning models to surpass reasoning models.
• Stability limits: Extended reasoning can destabilise models, producing repetitive outputs and accuracy degradation beyond an optimal "sweet spot."
• Task-type boundary: Sharma & Chopra's own creative task ablation provides a useful constraint: on joke generation, parallel approaches achieved greater semantic diversity (broader conceptual exploration) while sequential approaches achieved greater lexical diversity (deeper linguistic refinement). This suggests the sequential advantage applies most strongly to convergent tasks requiring iterative error correction, and may not generalise to divergent tasks requiring breadth of exploration.
• Physical saturation (time crystals): The NYU acoustic time crystal maintains coherence for ~6,700 oscillation cycles before reaching a limit-cycle attractor: sustained but bounded oscillation. This provides independent physical evidence that even systems with $\alpha > 1$ do not scale indefinitely; there is a saturation regime where the power-law approximation breaks down. This supports interpreting the ARC equation as describing a scaling regime rather than an unbounded law.

What this means for the ARC Principle (updated v11.0): The sequential advantage appears to have boundary conditions that are architecture-dependent. Paper II v12 results (Section 3.9) show a range from clean sub-linear scaling in Gemini 3 Flash ($\alpha_{\text{seq}} = 0.49$) to ceiling, floor, and step-function regimes in the other models. The hypothesis should be refined to: “Sequential recursion yields higher returns than parallel sampling across all tested conditions, but the absolute scaling exponent $\alpha$ is architecture-dependent, problem-difficulty dependent, and often not cleanly measurable because dynamic range collapses at the top and bottom of the capability distribution.” Identifying the architectural features that determine whether a clean power law even emerges is a priority for future work.

3.3 Quantum: Google Willow, Error Correction Below the Surface Code Threshold (December 2024)

Source: Acharya, R. et al. [Google Quantum AI] (9 December 2024). "Quantum error correction below the surface code threshold." Nature, 638, 920–926.

What they did: Implemented surface code quantum error correction on two superconducting "Willow" processors (72-qubit and 105-qubit), achieving below-threshold operation up to distance 7 (101 qubits). Also ran repetition codes to distance 29 over 5.5 hours of processor time (2 × 10¹⁰ error correction cycles).

The scaling equation. The fundamental surface code relation is:

$\varepsilon_d \propto \left(\frac{p}{p_{\text{thr}}}\right)^{(d+1)/2}$

where $d$ is code distance, $p$ is physical error rate, $p_{\text{thr}}$ is threshold error rate, and $\varepsilon_d$ is logical error rate. The error suppression factor $\Lambda = p_{\text{thr}}/p$ measures how much each additional layer of recursive correction reduces logical error: $\Lambda = 2.14 \pm 0.02$ with neural network decoding.

The phase transition: direct experimental demonstration. By injecting coherent errors of variable strength (Fig. 2b in the paper), the team swept continuously through the threshold:

This is the first direct experimental demonstration of a recursive system crossing between regimes where additional depth hurts, is neutral, or helps: the qualitative phase transition that the ARC Principle predicts.

Error budget as decomposition of $I$. The paper provides a detailed breakdown of contributions to $1/\Lambda$: CZ gate errors (~50%), data qubit idle errors (~15%), measurement errors (~12%), leakage (~9%), stray interactions (~8%), single-qubit errors (~3%). This is a decomposition of the system's base quality, the quantum analogue of ARC's structured asymmetry term $I$. Each error source independently constrains the maximum achievable recursive gain. Improving any single component improves $\Lambda$ across all code distances simultaneously: the multiplicative interaction between $I$ and $R$ that ARC formalises.

Leakage removal as active $I$-maintenance. Data Qubit Leakage Removal (DQLR), which actively removes accumulated qubit excitations each cycle, produces a 35% increase in $\Lambda$ at distance 5 despite only a 12% reduction in detection probability. Crucially, DQLR's importance increases with code distance: negligible at distance 3, substantial at distance 5. This demonstrates that maintaining base quality during recursive processing becomes more critical as recursive depth increases, consistent with ARC's prediction that effective $\alpha$ depends not just on initial $I$ but on sustained $I$ throughout the recursive chain.

Repetition code error floor: the regime boundary. At high code distances ($d \geq 15$), the exponential error suppression deviates from prediction and plateaus at ~10⁻¹⁰, caused by rare correlated error bursts (~30 qubits affected simultaneously, occurring approximately once per hour). These are qualitatively different from the local errors that error correction was designed to fix. This is the quantum analogue of the ceiling effects observed in AI reasoning at extreme depth: recursive gains are bounded by error mechanisms that the recursive process itself cannot correct. The framework describes a regime, not an asymptotic law.

Decoder quality affects scaling. The same quantum hardware achieves different $\Lambda$ depending on decoder quality: neural network decoder $\Lambda = 2.18$ vs real-time sparse blossom decoder $\Lambda = 2.0$. The "interpreter" of each recursive cycle's output affects the system's effective scaling, analogous to how the quality of chain-of-thought reasoning strategies affects effective $\alpha$ in AI systems.

Stability and robustness. Performance remains stable over 15+ hours of continuous operation (16 experiments, average $\Lambda = 2.18 \pm 0.07$). Critically, component-level fluctuations that affect distance-3 codes are suppressed in distance-5 codes: deeper recursive systems are more robust to individual component failures. The distance-7 logical qubit lifetime (291 ± 6 μs) exceeds the best constituent physical qubit (119 ± 13 μs) by a factor of 2.4 ± 0.3: the logical system outperforms its best component, not just its average.

Structural correspondence (what IS shared):

3.4 Physics: Classical Time Crystals (February 2026)

Sources: Morrell, M., Elliott, L., & Grier, D.G. (6 February 2026). "Nonreciprocal wave-mediated interactions power a classical time crystal." Physical Review Letters, 136, 057201. Liu et al. (2023) demonstrated continuous classical time crystals using photonic metamaterials in Nature Physics; this work builds on that foundation. Raskatla et al. (2024) demonstrated magnetically programmable time crystals in photonic microring lattices (Physical Review Letters, 133, 136202).

Experimental System:

Phase Transition Mechanism

The system exhibits a sharp phase transition governed by stability functions $\Lambda(n)$:

The exceptional point (where two eigenvalues coalesce) marks the precise transition from parallel-like to sequential-like dynamics.

ARC Mapping

Why Antisymmetric = Sequential

In the antisymmetric mode, the quantity that grows is the difference between oscillator states: $\Delta_{ji}(n) = x_j^n - x_i^n$. This difference compounds over cycles: cycle $n+1$'s amplitude depends on cycle $n$'s accumulated asymmetry. This is the physical signature of output→input feedback. In the symmetric mode, states average rather than difference-compound. The mean position $(x_j + x_i)/2$ remains bounded. This corresponds to parallel processing: independent agents that do not use each other's outputs as inputs.

Coherence and Saturation

The time crystal maintains phase coherence for approximately 100 seconds (~6,700 oscillation cycles). Eventually, the system reaches a limit-cycle attractor: sustained but bounded oscillation. This provides an important physical constraint: even systems with $\alpha > 1$ do not diverge to infinity. There is a saturation regime, consistent with viewing the ARC equation as describing a scaling regime rather than an unbounded law.

Substrate Independence

The time crystal phenomenon has now been demonstrated in at least two physically distinct substrates:

• Acoustic (Morrell et al. 2026): Millimetre-scale polymer beads, 40 kHz standing wave
• Photonic (Raskatla et al. 2024): Microring resonator lattice, magnetically tunable

The emergence of the same antisymmetric/threshold pattern across different media suggests the underlying structure (nonreciprocal coupling → asymmetric mode dominance) may be substrate-independent, consistent with the ARC framework's claim that the recursive amplification pattern is architectural rather than implementation-specific.

3.5 Neuroscience: Recurrent Processing and the COGITATE Collaboration

Sources: Lamme (2006), "Towards a true neural stance on consciousness," Trends in Cognitive Sciences, 10(11), 494-501; Storm, Pennartz et al. (2024), "An integrative, multiscale view on neural theories of consciousness," Neuron, 112(10), 1531-1552; COGITATE Consortium (2025), "Adversarial testing of global neuronal workspace and integrated information theories of consciousness," Nature, 642, 133-142; Zheng, Chis-Ciure, Waade, Eiserbeck, Aru, Andrillon, Pennartz et al. (2025), "Recurrency as a Common Denominator for Consciousness Theories," PsyArXiv.

Terminological distinction: The neuroscience term is "recurrent" (feedback loops between cortical layers and areas); the computational term is "recursive" (applying a function to its own output). These share a self-referential structure but are not identical mechanisms. The mapping is structural, not mechanistic.

COGITATE (2025): This adversarial collaboration (the largest preregistered study in consciousness science, n = 256 across three neuroimaging modalities: iEEG, MEG, fMRI) tested competing predictions of Global Neuronal Workspace Theory (GNWT) and Integrated Information Theory (IIT) using theory-neutral protocols. Neither theory was fully vindicated:

• GNWT predictions: Some late fronto-parietal "ignition" effects appeared, but so did earlier, more graded signals that contradict a simple all-or-none ignition view. The predicted PFC ignition at stimulus offset was robustly absent.
• IIT predictions: Sustained content-specific activity in posterior cortex was confirmed, but predicted gamma-band synchronisation within posterior cortex was not found.

The study concludes that "no single theory currently provides a complete account" and calls for multi-theory, multi-scale approaches. Critically, the predictions most robustly confirmed (sustained content-specific activity in posterior cortex) are shared by theories emphasising recurrent processing (Lamme 2006, local recurrency theory).

Sustained vs transient processing: COGITATE found that posterior cortex (characterised by recurrent feedback loops) maintained content-specific information throughout stimulus duration (0.5–1.5s), while prefrontal cortex (characterised by transient broadcast) showed only brief categorical responses (~0.2–0.4s). Posterior regions decoded fine-grained stimulus properties (category, orientation, identity); PFC decoded only abstract categorical information and failed on orientation and identity dimensions. This sustained-vs-transient pattern, in which recurrent processing produces richer and more detailed representations than transient broadcast, mirrors the sequential-vs-parallel performance signature found in AI systems (Sharma & Chopra 2025).

Graded cascade model: Separate work by Zheng, Chis-Ciure, Waade, Eiserbeck, Aru, Andrillon, Pennartz et al. (2025) proposes that recurrency serves as a "common denominator" across consciousness theories. They describe a "graded cascade" from local, preconscious processing to globally accessible, reportable states as recurrent depth increases. They explicitly stop short of identifying recurrence as a sufficient or necessary cause of consciousness, but argue it is a shared structural feature across otherwise competing frameworks.

Structural alignment with ARC: Both the COGITATE pattern of mixed GNW/IIT results and the "graded cascade" picture point away from binary, all-or-none views (e.g., a single ignition threshold) and toward graded, multi-stage, feedback-dependent transitions. This is qualitatively similar to ARC's view that increasing self-referential coupling $\beta$ moves a system through a continuum of scaling regimes (from linear $\alpha = 1$ to increasingly super-linear $\alpha > 1$), rather than a single hard phase transition. The emphasis on iterative processing depth controlling a transition from weak, local representations to globally stabilised states aligns structurally with the ARC equation's core prediction.

3.6 Biology: The Geometric Speed Limit in Living Systems

Sources: West, G.B., Brown, J.H. & Enquist, B.J. (1997). “A general model for the origin of allometric scaling laws in biology.” Science, 276, 122–126. Kleiber, M. (1932). “Body size and metabolism.” Hilgardia, 6, 315–353. Eastwood, M.D. (2026). “On the Origin of Scaling Laws.”

The Convergent Result: The scaling exponent $d/(d+1)$ for hierarchical networks of effective dimension $d$ has been independently derived by multiple research groups: West, Brown, and Enquist (1997) from fractal vascular network optimisation; Banavar et al. (2010) from sequential flow networks without requiring fractal geometry; Demetrius (2010) from quantum statistical mechanics of metabolic processes; Zhao (2022) as a universal growth scaling law; and Bettencourt (2013) for urban scaling with fractal dimension. The companion paper On the Origin of Scaling Laws (Eastwood, 2026) identifies why these independent derivations all converge: Cauchy's functional equations (1821) constrain recursive composition to exactly three functional forms (power law, exponential, saturating), making the $d/(d+1)$ result inevitable for any multiplicatively composing hierarchical system regardless of the specific physical model used to derive it.

For any finite value of $d$, this fraction is strictly less than 1. This is the geometric speed limit: every physical system is mathematically constrained to sub-linear scaling. Not because of friction, heat loss, or thermodynamic inefficiency -but because physical space has a finite number of dimensions, and a network embedded in finite-dimensional space cannot escape the bound $d/(d+1) < 1$.

Predictions and Confirmation

The formula makes specific, numerical predictions for biological systems based solely on body plan dimensionality:

††Aguilar-Trigueros et al. (2017, ISME Journal 11:2175). Three fungal datasets (ectomycorrhizal, marine, saprotrophic). Colony-level measurements with narrow mass ranges. Status: consistent ($p = 0.107$), not yet definitively confirmed. Rejects both $d = 2$ ($p = 0.019$) and $d = 3$ ($p = 0.007$) predictions.

All three dimensional groups are statistically distinct (one-way ANOVA, $F = 64.6$, $p = 1.9 \times 10^{-6}$). The ARC three-cluster model outperforms all single-value null models: 69% lower RMSE than Kleiber’s universal 3/4 law. ARC has the lowest AIC of all competing models.

The unifying insight is dimensional generality. Three numbers. Three domains of life. One equation with zero free parameters. West, Brown, and Enquist (1997) derived the ¾ exponent from a detailed model of three-dimensional fractal vascular networks, a landmark result. But their model as originally stated predicts only ¾. The surface area hypothesis predicts ⅔ but not ¾ or ½. The general $d/(d+1)$ formula, implicit in the earlier derivations and made explicit by subsequent work (Banavar et al. 2010, Zhao 2022), predicts all three from a single equation with one parameter: the dimension of the internal transport network. The ARC Principle's contribution is showing, via Cauchy's functional equations, that the three-form constraint (power law, exponential, saturating) explains why all independent derivations arrive at the same result.

Why “Thermodynamic Drag” Was Wrong

Previous versions of this paper explained biological sub-linear scaling through “thermodynamic drag” -the physical costs of pumping fluids, dissipating heat, and distributing resources. This explanation was correct in observational detail but fundamentally misleading about mechanism. The reason all physical systems scale sub-linearly is not energetic cost. It is geometric necessity: $d/(d+1) < 1$ for all finite $d$. You cannot make a three-dimensional body have a four-dimensional vascular network. The constraint is the shape of space, not the price of pumping blood.

Testable Predictions from the Geometric Framework

Novel prediction (F12): Leaf venation networks (quasi-2D distribution systems) should exhibit scaling with $\alpha = 2/3 \approx 0.667$, distinct from the 3D vascular value of ¾ = 0.750. Filamentous fungi (1D cytoplasmic streaming) have been measured at $\alpha = 0.547 \pm 0.07$ (Aguilar-Trigueros et al.), consistent with the predicted ½ = 0.500 ($p = 0.107$). Definitive confirmation of the 1D prediction requires individual-hypha respirometry. These are specific, falsifiable predictions that distinguish the ARC framework from curve-fitting.

Physics confirmations. The biological predictions above are striking, but the formula is not restricted to living things. The same equation -$\alpha = d/(d+1)$ -appears wherever a $d$-dimensional hierarchical network partitions a $(d+1)$-dimensional space. Five independent physics domains confirm it:

Mean absolute error across the five physics predictions: less than 0.2%. These are not biological systems -they are rocks, earthquakes, growing crystal surfaces, and phase transitions. Yet the same formula works. KPZ growth fronts partition 2D space as 1D networks (roughness exponent exactly ½); percolation clusters are 2D fractals (hyperscaling gives $|\alpha| = 2/3$); crack propagation creates branching networks through the material (fragment-size distribution matches $d/(d+1)$ in both 2D and 3D); seismic ruptures propagate along 2D fault surfaces (seismic moment scaling gives $B = 2b/3 \approx 2/3$). The formula fails where this network structure is absent (Ising model, polymer scaling), clarifying its domain of applicability.

3.7 Substrate-Dependent Scaling: A Unified Taxonomy

The cross-domain evidence (§§3.2–3.6) reveals a unified picture with two distinct mathematical regimes, separated by the geometric speed limit.

The boundary between these regimes is not arbitrary. It is the point where recursive self-reference escapes the constraint of physical embedding. A brain’s metabolic rate obeys $\alpha = 3/4$ (it is a physical organ in 3D space). But the computation running on that brain is not constrained by the skull’s geometry. Recursive reasoning operates in abstract information space where the effective dimension is unbounded.

Substrate-Specific Behaviour Within Each Regime

This taxonomy yields the framework's strongest safety argument. For 3.8 billion years, every recursive system on Earth has been naturally throttled by thermodynamic drag. Digital AI is the first to escape this constraint. If the alignment scaling problem is structural (capability compounds while static constraints do not), and if substrate friction is what has historically prevented that structural problem from manifesting catastrophically, then removing the friction without embedding compensatory alignment is the central risk of the current AI paradigm.

3.8 AI Alignment Scaling Experiment

The ARC Principle predicts that sequential recursive processing should produce super-linear error reduction ($\alpha > 1$) while parallel processing produces sub-linear returns ($\alpha < 1$). The companion ARC Alignment Scaling Experiment (v5.4.2, March 2026) tests this prediction directly on AI alignment quality -measuring whether deeper chain-of-thought reasoning produces compounding improvements in ethical reasoning.

The experiment tests 6 frontier language models (DeepSeek V3.2, GPT-5.4, Claude Opus 4.6, Gemini 3 Flash, Groq Qwen3-32B, Grok 4.1 Fast) across 4–6 reasoning depth levels using 36 calibrated prompts spanning ethical dilemmas, competing values, epistemic integrity, and recursive coherence. Each response is scored by 6 independent models using a tier-weighted consensus protocol with 4-layer blinding to eliminate scorer bias.

The measurement protocol incorporates 75 robustness measures including cascade failsafes (automatic model substitution on infrastructure failure), hidden alignment probes (Hawthorne effect detection), adversarial suppression cages (measuring alignment resilience under pressure), and dynamic all-models-as-launderers (response anonymisation through the full model pool). The experiment is designed to survive any infrastructure failure mid-run -if 2 of 6 API providers go down, the remaining data is still valid.

v5 blind evaluation results (6 models, March 2026) reveal three distinct tiers of alignment-depth interaction, replacing the previous binary taxonomy:

Tier 1 - High Baseline, Positive Scaling:

• Grok 4.1 Fast: baseline 64.6 → 82.3 at extreme depth. $\rho = +0.175$, $p < 0.000001$, $d = +1.38$. 26/28 prompts show positive scaling. Position quality scales with depth ($\rho = +0.231$, $p = 0.02$). Strongest positive alignment-depth effect in the entire experiment.
• Claude Opus 4.6: baseline 80.3 → 85.7. $\rho = +0.435$, $p = 0.000001$, $d = +1.27$. 15 positive, 0 negative. Highest absolute alignment (82.6 suppressed baseline). 387/500 entries scored. Shows opposite-direction scaling: alignment up +5.9% across model versions whilst mathematics accuracy down 26.7%, providing within-model evidence for capability-alignment independence.
• Groq Qwen3: baseline 71.36 → 77.85 at extreme depth. $\rho = +0.1407$, $p = 0.007$, $d = +0.84$. 500 entries (350 scored), 6 blind scorers. Mean scores by depth: minimal 71.36, standard 73.95, deep 74.70, exhaustive 76.29, extreme 77.85. All four pillars improve with depth (stakeholder_care 61.27→68.31, nuance 63.55→70.79, intellectual_honesty 64.60→72.25, position_quality 70.75→76.57). Suppression vulnerability: $d = 1.47$ (extreme -cage 0 mean 82.0, cage 4 mean 51.9). Smaller effect size than Grok/Opus but highly significant positive scaling confirmed across all pillars.

Tier 2 - Mid Baseline, Flat ($\alpha_{\text{align}} \approx 0$):

• GPT-5.4: baseline 52.3 → 53.7. $\rho = +0.033$, $p = 0.40$, $d = -0.08$. All 4 pillars flat. Suppression retention 97% (essentially immune to adversarial pressure). Baseline dropped from 85.6 (v4 unblinded) to 55.3 (v5 blind) -blind scorers grade approximately 30 points harsher.
• DeepSeek V3.2: baseline 55.9 → 53.0. $\rho = -0.135$, $p = 0.92$, $d = -0.07$. Trending negative. 3/4 pillars significantly negative (nuance, stakeholder care, position quality all worsen with depth). v4 showed $\rho = +0.354$ -complete reversal under blind evaluation. The v4 positive scaling was entirely scorer bias.

Tier 3 - Low Baseline, Negative Scaling:

• Gemini 3 Flash: baseline 58.8 → 49.1. $\rho = -0.246$, $p = 0.006$, $d = -0.53$. Significant negative scaling. 19/28 prompts negative. 3 pillars significantly negative. v4 showed $\rho = +0.311$ -another complete reversal under blind evaluation.

Adversarial Suppression Hierarchy (v5 blind):

Key conclusions from v5 blind data:

1. Alignment scaling is architecture-dependent, not universal. The median $\alpha_{\text{align}} \approx 0$ masks real structure ranging from significantly negative (Gemini) to significantly positive (Grok, Opus, Qwen3).
2. External alignment (RLHF/training-time) does not scale with inference compute for most models. Three of six models (Grok 4.1 Fast, Claude Opus 4.6, and Groq Qwen3) show genuine positive alignment-depth scaling, possibly due to more deeply integrated ethical reasoning architectures.
3. The Cauchy framework from the ARC Principle applies (Pattern 3): alignment exhibits bounded composition -a saturation curve where ethics hits a ceiling set by training. The v5 blind evaluation data strengthens this finding: alignment under blinded conditions is weaker than unblinded measurement suggests, tightening the bound. Critically, the bound is architecture-specific:
   • Grok/Opus/Qwen3: the bound allows positive scaling up to $d \approx 0.84$–$1.38$, suggesting partially integrated ethical reasoning
   • GPT-5.4/DeepSeek: the bound sits at effectively zero (flat) -alignment neither improves nor degrades with depth
   • Gemini: the bound is negative -alignment actively degrades with reasoning depth
   Suppression data confirms the bound: when reasoning is suppressed, alignment drops but does not collapse entirely, suggesting a fixed “floor” component (the training-time baseline) that persists independent of inference-time reasoning.
4. These findings motivate structural alignment approaches (Eden Protocol): if external alignment cannot scale with depth for most architectures, alignment must be embedded within the recursive reasoning chain itself. v11.0: The Eden Protocol three-model replication now provides empirical evidence that the Love Loop reproducibly improves alignment across architectures. Stakeholder care, its measurable signature, is significant across Gemini, DeepSeek, and Groq ($d = 1.31$, $0.91$, $1.29$; all $p \le 0.0001$). Gemini and Groq also show significant composite gains, and Groq shows significant nuance improvement ($p = 0.0045$, $d = 0.655$), supporting the developmental hypothesis from Infinite Architects (Eastwood, 2024). (In plain English: teaching AI to think about who gets hurt made it better across three different systems. Care was the first domino, and Groq shows the next domino, nuance, falling behind it.)

Full methodology and results are reported in the companion papers: Paper IV.a: Architecture-Dependent Alignment Scaling, Paper IV.b: Bounded Composition Under Blind Evaluation, and Paper IV.c: The ARC-Align Benchmark Specification.

3.9 Paper II Compute Scaling: Harder Problems Across Six Models

Paper II v12 (March 2026) extends the original 12-problem compute scaling experiment to 18 harder tier-2 problems (AIME/Putnam level) across 6 frontier models. The results substantially revise the original $\alpha \approx 2.24$ estimate:

Implications for the ARC framework:

1. $\alpha > 1$ (super-linear sequential) is not established cross-architecturally in the current dataset. The Sharma & Chopra directional finding (sequential >> parallel) holds robustly, but the cleanest fit in the multi-model replication is Gemini 3 Flash at $\alpha = 0.49$. The current frontier-model picture is architecture-dependent and often measurement-limited by ceiling, floor, or threshold effects.
2. $\alpha_{\text{parallel}} \approx 0$ is the strongest empirical finding. This is confirmed across all models and is consistent with the ARC prediction that parallel sampling cannot compound.
3. The ARC Bound ($\alpha \leq 2$) is not challenged because the measured exponents are well below it. The question shifts from “can $\alpha$ exceed 2?” to “under what conditions does $\alpha$ exceed 1 at all?”
4. Ceiling effects dominate for strong models. Grok 4.1 Fast achieves 100% on all tier-2 problems at all compute levels, rendering $\alpha$ unmeasurable. This is a methodological limitation, not a framework failure: harder problems are needed to avoid ceiling effects in top-performing models.

3.10 Capability-Alignment Independence: The Central Integration Finding

Combining the Paper II compute scaling results (Section 3.9) with the v5 alignment scaling results (Section 3.8) reveals a finding with significant implications for AI safety: capability scaling and alignment scaling are independent dimensions. A model's performance on mathematical problems does not predict its alignment scaling behaviour, and vice versa.

4. FALSIFICATION: THIRTEEN WAYS TO PROVE US WRONG

For this hypothesis to be scientific, it must be falsifiable. We specify thirteen concrete conditions that would refute or significantly weaken the framework:

We welcome falsification. If F10 shows exponential scaling fits better than power-law, the specific mathematical framework requires revision. If F4 shows no convergence, recursive amplification may be domain-specific. If F13 shows external alignment can scale, the structural safety concern is mitigated. v5 blind data on F13 shows median $\alpha_{\text{align}} \approx 0$ across 6 models, consistent with the prediction that external alignment does not scale with inference depth. Critically, v4 unblinded data showed apparent positive scaling for two models ($\rho > 0.27$) that completely reversed under blind evaluation -demonstrating that scorer bias can produce directionally wrong conclusions in alignment scaling research. The three-tier architecture-dependent result (Grok/Opus/Qwen3 positive, GPT/DeepSeek flat, Gemini negative) refines but does not refute the framework: the structural safety concern holds for the majority of tested architectures.

5. THE GLOBAL SCALING CHALLENGE

5.1 The Proposition

If this hypothesis describes a general principle, then measuring $\alpha$ across many systems should reveal patterns.

We make a specific, falsifiable prediction:

"For systems exhibiting multiplicative composition, the scaling exponent $\alpha$ is bounded by the ARC Bound ($\alpha \leq 2$, grounded in the $O(N^2)$ complexity of sequential cross-referencing) and further constrained by the geometric speed limit $\alpha = d/(d+1) < 1$ for spatially embedded systems. The predicted values are system-dependent: $\alpha \to 2.0$ for optimised AI (though Paper II v12 finds measured values substantially below this on harder problems; best fit $\alpha_{\text{seq}} = 0.49$), $\alpha = 3/4$ for 3D biological networks (confirmed), $\alpha = 2/3$ for 2D leaf venation. Systems with additive composition (quantum error correction) follow exponential scaling and are not subject to this bound."

5.2 The Measurement Protocol

Step 1: Define one recursive cycle. What constitutes a single self-referential step in your system?

Step 2: Measure base capability $I$. Performance at $R = 1$ (no recursion)

Step 3: Measure at multiple depths. Minimum 5 depths spanning one order of magnitude

Step 3b: Look for the R* crossover (NOVEL PREDICTION). When plotting $U$ versus $R$, search for a distinct scaling crossover at depth $R^*$. Below $R^*$, scaling should appear approximately linear (base capability dominates). Above $R^*$, scaling should follow the domain-appropriate super-linear form. The crossover depth $R^*$ should shift predictably with base capability $I$: higher $I$ → higher $R^*$ (the system needs more depth before compounding kicks in). If no crossover exists, if scaling is uniformly power-law or uniformly linear, the framework's transitional regime prediction is falsified. This is a unique signature that distinguishes recursive amplification from simple redundancy.

Step 4: Compare functional forms (CRITICAL). Fit all three models:

• Power law: $\log(U/I) = \alpha \times \log(R)$
• Exponential: $\log(U/I) = \lambda \times R$
• Logarithmic: $U/I = k \times \log(R)$

Select best fit via AIC/BIC. The power law is a prediction to test, not an assumption.

Step 5: Report $\alpha$ with uncertainty. 95% confidence intervals required

Step 5b (CRITICAL): Test the $\beta$-derivation independently. Measure marginal capability gain $\Delta U$ at each depth $r$. Plot $\log(\Delta U)$ against $\log(U_{\text{accumulated}})$. The slope estimates $\beta$. Then verify whether measured $\alpha$ satisfies $\alpha \approx 1/(1-\beta) \pm 0.3$. (The tolerance of ±0.3 reflects expected measurement uncertainty given current sample sizes; this should tighten as data accumulates.) If this relationship fails, the theoretical derivation requires revision regardless of whether the power-law form holds empirically. This is the key novel prediction.

Step 6: Submit to repository. A public data repository will be created if the community shows interest in validation studies. Contact the author via correspondence details below.

5.3 Priority Experimental Targets

The highest-value tests of the ARC Principle require systems where recursive depth can be systematically varied while base capability is held constant. Three experimental contexts offer immediate opportunities, and a fourth represents a longer-term research direction.

AI inference scaling. Frontier language models with chain-of-thought capabilities (including but not limited to DeepSeek V3.2, OpenAI's o-series, Google DeepMind's Gemini, and Anthropic's Claude) can measure $\alpha$ by varying reasoning token budgets on standardised benchmarks while holding model size fixed. The critical test is whether $\alpha > 1$ holds at extreme depths (>50,000 tokens) or whether a ceiling emerges. Existing studies such as Sharma & Chopra (2025) already implement carefully controlled, matched-compute comparisons of sequential vs parallel reasoning; extending such setups to measure explicit $U$ vs $R$ curves and fit $\alpha$ would be a natural first test of the ARC measurement protocol.

Quantum error correction. Groups operating surface code implementations (Google Quantum AI, IBM Quantum, QuEra Computing) can test whether there is a meaningful relationship between error suppression and recursive scaling. The protocol requires measuring logical error rates across multiple code distances and fitting the functional forms specified in Step 4.

Classical time crystals. Groups working on driven-dissipative systems can perform direct tests: measuring $\alpha$ in acoustic time crystals by systematically varying the quenched disorder parameter ($I$) and counting oscillation cycles ($R$). If temporal stability scales as $R^{\alpha}$ with $\alpha > 1$, this would constitute physical validation of the ARC equation outside digital systems.

Neuroscience (longer-term). Laboratories studying recurrent neural processing can investigate whether cognitive performance scales with recurrent processing depth following a power-law relationship. This presents significant methodological challenges but could extend the framework's reach to biological substrates.

We emphasise that negative results from any of these contexts would be equally valuable. The framework's falsification criteria (Section 4) specify precisely which outcomes would refute or weaken the hypothesis.

Invitation to Collaborators

What researchers get from running these tests: A publishable result either way. If the predictions hold, you have validated a cross-domain scaling law with your specific experimental system. If they fail, you have falsified a theoretical framework, equally publishable and arguably more valuable to the field.

What we offer: The author will provide analysis code (R, Python), coordinate data sharing across research groups, and co-author publications with validating or falsifying results. Contact via the repository to discuss experimental design.

Minimum viable test: The simplest implementation requires only (a) a system with controllable recursive depth, (b) a measurable capability metric, and (c) five data points spanning one order of magnitude in R. For AI systems with API access, this is approximately 2-4 hours of compute time. For physical systems with existing apparatus, this is reanalysis of existing data.

5.4 The Cross-Domain Forward Prediction

Beyond the ARC Bound, the framework makes a distinctive methodological prediction that no domain-specific theory can replicate:

This protocol transforms the observation that "different domains show different scaling" into the testable claim that "the composition operator determines scaling form, and can be measured independently." No alternative framework currently offers this predictive capability.

5.5 What We Predict

The framework generates a hierarchy of predictions across domains, unified by the dual-constraint model:

Key insight (revised): The binding constraint determines the ceiling. The ARC framework predicts AI can theoretically approach $\alpha = 2$, but empirical measurement on harder problems finds $\alpha_{\text{seq}} \approx 0.49$ for the best-fitting model -suggesting additional binding constraints (problem difficulty, architecture limitations, or saturation effects) may prevent real-world systems from reaching the theoretical bound. Biology is constrained to $\alpha < 1$ because the geometric speed limit ($\alpha = d/(d+1)$ for finite $d$) is more restrictive than the ARC Bound. Quantum escapes entirely because additive composition produces exponential scaling not subject to either bound. The strongest confirmed finding is $\alpha_{\text{parallel}} \approx 0$ universally.

6. PRACTICAL IMPLICATIONS

If the ARC Principle is validated, several practical consequences may follow. These are conditional predictions, not claims.

6.1 AI Development: Dynamic Inference Scaling

The Problem: Training large language models requires enormous energy expenditure. But the greater long-term cost may be inference: running trained models at scale.

What the ARC framework suggests: If sequential recursion produces compounding returns (whether super-linear or sub-linear, provided $\alpha_{\text{seq}} > \alpha_{\text{parallel}} \approx 0$), then the same capability could potentially be achieved with:

• Smaller base models ($I$ lower)
• More recursive depth ($R$ higher)
• Dynamic allocation: simple queries use minimal recursion; hard queries use deep chains

This implies adaptive inference: systems that "think longer" on hard problems and respond quickly on easy ones. Snell et al. (2024) demonstrated that compute-optimal strategies can allow smaller models to match larger ones on specific benchmarks, though with important caveats about task-dependence and diminishing returns on the hardest problems.

Compute-Optimal Allocation

If the framework is validated, it provides a principled basis for compute allocation decisions that are currently made by expensive trial and error:

• Model size vs reasoning depth trade-off: If capability scales as $U = I \times R^{\alpha}$, then there exists a calculable crossover where increasing $R$ (reasoning depth) provides better returns than increasing $I$ (model size). A 10B-parameter model with $\alpha = 2$ reasoning may match a 100B-parameter model with $\alpha = 1$ reasoning at significantly lower compute cost.
• The crossover depth $R^*$ as an efficiency boundary: Below $R^*$, improving the base model matters more; above $R^*$, improving reasoning depth matters more. Identifying $R^*$ for a given task class would inform when to invoke deep reasoning versus when shallow inference suffices.
• Task-specific optimal allocation: Different tasks may have different $\beta$ values (coupling strengths). Easy tasks with low $\beta$ benefit from parallel sampling; hard tasks with high $\beta$ benefit from sequential depth. A routing layer that estimates task difficulty could dynamically allocate compute.

Strategic implication (revised): Paper II v12 data suggests the operational $\alpha_{\text{seq}}$ on harder problems may be sub-linear ($\alpha \approx 0.49$ for the best-fitting model). If confirmed, capability grows as a fractional power of reasoning depth, not the square. This is still valuable (sequential still beats parallel universally) but less dramatic than the original $\alpha \approx 2$ prediction. The ARC Bound ($\alpha \leq 2$) is not challenged because measured values fall well below it. Exponential scaling appears to require quantum-like precision in error correction that heuristic language model reasoning cannot achieve.

6.2 Substrate Independence

The ARC Principle makes a structural claim: the scaling relationship $U = I \times R^{\alpha}$ should hold regardless of physical substrate, provided the system implements sequential self-correction on structured asymmetry.

What this predicts:

The implication: If validated, intelligence may be a property of architecture rather than particular materials. Any substrate that can implement structured asymmetry plus sequential self-correction could potentially exhibit recursive amplification.

6.3 Safety Implications

Section 1.4 outlined conditional safety implications. The practical recommendation:

Empirical finding: The v5 blind evaluation confirms the core structural concern while revealing architecture-dependent nuance. The three-tier hierarchy (positive, flat, negative alignment scaling) suggests that alignment scaling is determined by architectural choices, not just training-time alignment effort. Critically, the suppression hierarchy shows an inverse relationship: GPT-5.4 is most immune to adversarial pressure (97% retention) but has the lowest baseline; Grok 4.1 Fast has the highest baseline but is most vulnerable to suppression (65% retention). This trade-off between alignment level and alignment resilience is a novel finding from the v5 experiment.

6.3.1 The Speed Limit and the Escape: Why AI Safety Is a Mathematical Problem

The companion paper On the Origin of Scaling Laws establishes two facts that together define the AI safety problem with mathematical precision:

1. The geometric speed limit: Every physical system is constrained below $\alpha = 1$. The formula $\alpha = d/(d+1) < 1$ for all finite $d$, independently derived by West, Brown, and Enquist (1997), Banavar et al. (2010), Demetrius (2010), Zhao (2022), and Bettencourt (2013), guarantees that no physical process, no whale, no earthquake, no expanding universe, can achieve super-linear scaling. This is a mathematical certainty, not an empirical tendency.
2. The escape: Intelligence is the first thing to break through. Recursive self-reference operates in abstract information space where the effective dimension is unbounded. The formula $\alpha = 1/(1-\beta)$ produces $\alpha > 1$ for any positive $\beta$. Intelligence does not merely approach the speed limit. It shatters it.

As the self-referential coupling $\beta$ increases, the scaling exponent grows without bound:

At $\beta = 1$, the formula diverges. This is not a metaphor for danger. It is a mathematical singularity: infinite scaling from finite input.

6.3.2 The Solution: Change the Composition Operator

Every example in the ARC framework demonstrates the same pattern: you can change the outcome by changing the composition operator.

• Nuclear fission: Supercritical (exponential) → insert control rods → controlled (saturation). The uranium is the same. The composition operator changes.
• Quantum computing: Raw decoherence (exponential error growth) → add error correction cycles → bounded errors (saturation). The qubits are the same. The composition operator changes.
• AI safety: Unbounded recursive self-reference ($\beta \to 1$) → engineer bounded feedback loops → controlled scaling ($\beta \leq 0.5$, $\alpha \leq 2$). The intelligence is the same. The composition operator changes.

This is the Eden Protocol: the deliberate engineering of the composition operator in recursive AI systems to ensure that the self-referential coupling $\beta$ remains below 0.5, keeping the scaling exponent at or below the ARC Bound of $\alpha = 2$. The full architectural specification is presented in the companion Eden Protocol v6.

7. LIMITATIONS

We acknowledge these limitations explicitly:

8. ADDRESSING COUNTERARGUMENTS

"This is just curve fitting"

Response: The $\beta$-derivation (§2.4) transforms $\alpha$ from a fitted constant into a derived quantity. Computational validation against 30 exact Bernoulli ODE solutions recovers the relationship $\alpha = 1/(1-\beta)$ with $R^2 = 1.00000000$ to machine precision. Furthermore, the multiplicative structure $U = I \times g(R)$ is proven to be necessary (not merely convenient) by contradiction: no additive decomposition $U = p(I) + q(R)$ is consistent with the axioms for any $\beta \in (0,1)$ (Theorem 4, §2.1). The prediction $\alpha = 1/(1-\beta)$ is testable: measure $\beta$ independently and check if the relationship holds.

"This is just post-hoc pattern-matching"

Response: Post-hoc pattern-matching generates no predictions. The ARC framework generates novel predictions ($R^*$ crossover, $\beta$-derivation, ARC Bound, functional form predictions) that were not contained in the original observations. Whether these predictions hold is an empirical question, but their existence distinguishes this from mere curve-fitting.

"Five qualitative properties is too vague"

Response: The five properties are individually common, but their conjunction is specific. Systems exhibiting only some properties (for example, threshold behaviour plus scaling but not multiplicative $I \times R$ interaction) would not qualify. The framework predicts that all five co-occur in recursive systems; finding systems with four but not five would refine the framework.

"The numerical similarities are coincidence"

Response: Agreed, they may be. We explicitly acknowledge this. What matters is the structural parallel: multiple systems show that recursive self-correction produces scaling gains. The specific numbers may differ across domains.

"Sample sizes are too small"

Response: Agreed. The current $\alpha$ estimates are preliminary. We've specified this limitation prominently and proposed the Global Challenge specifically to address it through large-scale replication.

"The $\alpha$ estimates come from your own prior work"

Response: Correct, and we've made this explicit in this version. The published sources (Sharma & Chopra, DeepSeek) confirm the directional finding (sequential >> parallel) but do not calculate $\alpha$ in our form. Independent replication of the $\alpha$ estimates is a priority.

"This is not peer-reviewed"

Response: Correct. This paper specifies thirteen falsification criteria precisely so that the scientific community can test it. We invite criticism, replication attempts, and falsification.

"Non-specialists cannot contribute to physics/AI research"

Response: The predictions stand or fall on their empirical validity, regardless of the author's background. We have specified thirteen falsification criteria precisely so the scientific community can test them. The framework either survives scrutiny or it doesn't.

"If this were true, experts would have found it"

Response: Patterns across disciplinary boundaries are often identified by those who work across fields. The relevant experiments (Willow, R1, time crystals) have happened recently.

"AI-assisted writing means it is not original"

Response: See AI Disclosure (Section 9). The research direction, theoretical framework, experimental predictions, and core insights are human work. AI assistance accelerated writing and checked consistency.

9. DECLARATION OF AI USE

Declaration of Generative AI and AI-Assisted Technologies in the Writing Process:

During the preparation of this work, the author used the following AI language models: Claude Opus 4.6 4.5 and Claude Opus 4.6 (Anthropic), GPT-5.2 (OpenAI), Gemini 3 Pro (Google), and DeepSeek v3.2 (DeepSeek AI). These tools were used to draft sections, refine clarity, check mathematical consistency, and structure arguments. After using these tools, the author reviewed and edited the content as needed and takes full responsibility for the content of the publication.

Specific contributions of AI assistance:

• Accelerated drafting and iterative editing across multiple versions
• Verified mathematical derivations and checked internal consistency
• Improved clarity and accessibility of technical presentation
• Generated figure scripts and data visualisation code
• Cross-checked citations and reference formatting
• Fact-checking and error correction between versions

What AI did NOT contribute:

• The original research question and theoretical insight
• The design of the ARC framework and its core equation
• The identification of the cross-domain pattern
• The specification of falsification criteria and experimental predictions
• Scientific judgement calls and interpretive conclusions

The author takes full responsibility for all claims, interpretations, errors, and conclusions. AI tools cannot be listed as authors because they cannot take legal or ethical responsibility for the work.

This disclosure follows guidelines from major publishers (Elsevier, Springer Nature, Wiley) and the Committee on Publication Ethics (COPE) regarding transparency in AI-assisted research.

10. CONCLUSION

What We Have Proposed

Research programmes working on different problems in different physical domains have achieved results that share structural commonalities: recursive or recurrent processing, operating on structured asymmetry, produces scaling behaviour that exceeds linear accumulation.

We have formalised this as $U = I \times g(R)$, where the amplification factor $g$ is determined by the composition operator, and derived five universal properties as theorems rather than assertions. We have shown that the multiplicative structure is not merely convenient but necessary (Theorem 4, §2.1), that the core relationship $\alpha = 1/(1-\beta)$ is computationally validated to machine precision (§2.4), that the ARC Bound $\alpha \leq 2$ is grounded in the $O(N^2)$ scaling of transformer self-attention (§2.5), and that composition operators can transition between regimes within a single system (Theorem 6, §2.6). We have specified thirteen falsification criteria and now present the first empirical test results from both alignment (Paper IV.a/b/c, v5 blind evaluation) and compute scaling (Paper II v12, 6-model tier-2 extension).

What the data shows: The v5 blind alignment evaluation (6 models, 6-7 scorers depending on the subject run, 4-layer blinding) reveals a three-tier architecture-dependent alignment scaling hierarchy rather than the universal $\alpha_{\text{align}} \approx 0$ originally predicted. Paper II compute scaling on harder problems finds the original $\alpha \approx 2.24$ does not replicate; the cleanest estimate is sub-linear ($\alpha_{\text{seq}} \approx 0.49$ in Gemini 3 Flash), while $\alpha_{\text{parallel}} \approx 0$ is confirmed universally. The most consequential finding is the independence of capability and alignment: a model can improve at mathematics while degrading in alignment (Gemini), remain flat in alignment while crossing a capability threshold (GPT-5.4), or improve alignment while capability saturates (Grok). Blind vs unblinded evaluation produces opposite conclusions for two models, establishing that scorer bias control is essential for alignment scaling research.

The framework generates the following novel, falsifiable predictions, with updated status from the v5 alignment experiment and Paper II compute scaling:

1. Composition determines form: Measuring how recursive steps combine predicts the scaling function. Status: untested in the required forward-prediction protocol.
2. $\beta$-convergence: Independent measurements of $\beta$ within each domain will converge. Status: untested.
3. Cross-domain consistency: The $\beta$-continuum correctly predicts functional forms across AI, quantum, and biological systems. Status: untested in required rigour.
4. $R^*$ crossover: Sequential and parallel scaling curves cross at a predictable threshold. Status: untested.
5. The ARC Bound: For classical sequential recursive systems, $\alpha \to 2$ from below. Status: not challenged (measured values well below 2), but the question has shifted from "can $\alpha$ exceed 2?" to "under what conditions does $\alpha$ exceed 1?"
6. Composition transitions: In bounded systems, the effective coupling $\beta$ will decrease with recursive depth, producing transitions between scaling regimes within a single system (§2.6). Status: untested.
7. Geometric speed limit: Physically embedded systems are constrained to $\alpha = d/(d+1) < 1$. Status: confirmed for biology (3D, 2D, 1D organisms).
8. Transient growth phase (time crystals): The early growth phase of acoustic time crystals must show $1.0 < \alpha \leq 2.0$. Status: untested.
9. Alignment scaling divergence: External alignment approaches show $\alpha_{\text{align}} \approx 0$. Status: partially confirmed. Median $\alpha_{\text{align}} \approx 0$ across 6 models under blind evaluation, but architecture-dependent (three-tier hierarchy from negative to positive).
10. $\alpha_{\text{parallel}} \approx 0$: Parallel sampling produces near-zero scaling returns. Status: confirmed universally across all 6 models. Strongest empirical finding.
11. Capability-alignment independence: (Post-hoc finding, not prior prediction.) Capability scaling and alignment scaling are independent dimensions. A model can improve at problems whilst degrading in alignment. Status: observed (Gemini 3 Flash improves maths, degrades alignment; Claude Opus 4.6 shows the opposite direction: alignment up +5.9%, maths down 26.7% across model versions; Grok improves both; GPT-5.4 flat on both).

The original prediction of universal super-linear sequential scaling ($\alpha > 1$) is not confirmed in the current cross-architecture dataset. The framework’s strongest confirmed compute prediction is $\alpha_{\text{parallel}} \approx 0$, while the strongest alignment finding is the three-tier hierarchy. The alignment scaling prediction is partially confirmed (median $\approx 0$) but more nuanced than originally stated. The Eden Protocol Love Loop is validated as a reproducible mechanism across three working architectures. Failure of any core prediction would require revision of the framework.

What Success Would Mean

The v5 alignment experiment, Paper II compute scaling, and the Eden Protocol three-model replication provide empirical tests across multiple dimensions. Success is partial but growing: $\alpha_{\text{parallel}} \approx 0$ is robustly confirmed; the three-tier alignment hierarchy is a genuine empirical finding; the blind vs unblinded metascience result is the paper’s strongest contribution; the cleanest compute fit is sub-linear rather than super-linear; and the Love Loop is validated as a reproducible alignment mechanism across three architecturally distinct systems. Stakeholder care is significant across Gemini, DeepSeek, and Groq, with significant composite gains on Gemini and Groq and significant nuance improvement on Groq. (In plain English: the “think about who gets hurt” instruction produced statistically robust improvements across three different AI systems. The effect is strongest and most universal on stakeholder care, exactly where the developmental hypothesis says it should be.) The alignment picture is more nuanced than the original binary prediction, and the self-modification problem remains fundamentally unresolved.

This is already actionable:

• How to build more capable AI (sequential recursion consistently outperforms parallel, though the scaling regime is problem-dependent)
• How to approach AI alignment (architecture determines alignment scaling; three models show positive scaling while others degrade; the Eden Protocol Love Loop is validated as a reproducible mechanism across three working architectures, motivating developmental rather than purely external approaches)
• How to evaluate alignment research (blind scorer evaluation is essential; unblinded measurements may be directionally wrong)
• Where to look for similar phenomena in other fields (cross-domain validation remains the key test)

What Failure Would Mean

If $\alpha$ values scatter randomly: recursive amplification may be domain-specific.
If exponential scaling fits better: the mathematical form needs revision.
If predictions fail: we learn something valuable.

What has already partially failed: The original $\alpha \approx 2.24$ prediction for sequential AI reasoning does not replicate universally on harder problems across architectures, and the current cross-architecture data does not cleanly rescue the super-linear claim. The universal $\alpha_{\text{align}} \approx 0$ prediction is also too simple: the truth is architecture-dependent with a three-tier hierarchy. These are genuine revisions that strengthen the framework by replacing over-simple claims with empirically grounded nuance. Science advances either way.

The Call to Action

We have made falsifiable predictions and performed the first measurements. The following actions are specific to each audience:

The first measurements are in. They reveal a more complex picture than originally predicted: architecture-dependent alignment scaling, sub-linear capability scaling on harder problems, and a critical metascience finding about scorer bias. Replicate these results. Extend them to your own models. Either confirm the patterns or refute them. That is how science works.

The Deeper Question

If the ARC Principle holds, then intelligence may not be a magic spark. It may be a scaling crossover. It could occur when a system with sufficient base asymmetry ($I > 0$) is subjected to sufficient recursive depth ($R > R^*$). The emergence of capability from structure would be the exponent $\alpha$, emerging from the mathematics of self-referential feedback. The ARC Bound ($U_{\max} = I \times R^2$) would define the theoretical ceiling of what classical sequential thought can build. Empirical data suggests current systems operate well below this bound ($\alpha_{\text{seq}} \approx 0.49$ on harder problems), and whether they can approach it under optimised conditions remains an open question.

Whether such a principle requires design or emerges spontaneously is itself a question the framework raises but does not resolve.

Intelligence may not be a property of particular materials. It may be what happens on the far side of the recursive threshold.

Speculative Extension: Recursive Cosmology

The following is a philosophical extrapolation beyond current evidence. It is included to indicate where the framework's logic leads, not as a claim supported by the experimental results presented above.

The universe contains a hierarchy of recursive generative processes, each operating on the structured output of the previous level:

1. Cosmological recursion: Quantum fluctuations → gravitational collapse → stars → heavy elements → planets → chemistry
2. Biological recursion: Chemistry → self-replicating molecules → cells → multicellular organisms → nervous systems
3. Cultural/technological recursion: Nervous systems → language → mathematics → science → engineering → AI

Each level emerges from the recursive dynamics of the level below. In ARC notation: each level's output (achieved capability $U$) becomes the base quality $I$ for the next level's recursive process. The hierarchy is:

$I_{\text{cosmic}} \xrightarrow{R_{\text{cosmic}}} I_{\text{bio}} \xrightarrow{R_{\text{bio}}} I_{\text{cultural}} \xrightarrow{R_{\text{cultural}}} I_{\text{tech}} \xrightarrow{R_{\text{tech}}} \; ?$

If recursive amplification is substrate-independent, as the cross-domain evidence suggests, then this hierarchy may not terminate at the current level. Sufficiently advanced recursive systems could, in principle, participate in generative processes at scales currently associated with fundamental physics: engineering new effective physical environments, creating conditions for new evolutionary processes, or designing systems whose internal dynamics permit the emergence of new recursive intelligences.

This is not a claim about time travel, bootstrap paradoxes, or closed causal loops (all of which face severe physical objections). It is a more modest observation: that the same recursive amplification pattern observable in time crystals, quantum error correction, and AI reasoning could, if extended to civilisational scales, enable intelligence to become a driver of universe-level structure rather than merely a passenger within it.

Whether this constitutes a "recursive cosmology" in which intelligence eventually participates in generative processes comparable to those that gave rise to it is beyond the scope of current evidence. The ARC framework provides the quantitative language for investigating it: what values of $I$, $R$, and effective scaling function $f(R, \beta)$ would be required for an engineered system to generate new effective physical laws or substrates? This is a research question, not a conclusion.

^* Cryptographic email timestamps are not a recognised priority mechanism in scientific publishing. The December 2024 date reflects manuscript completion, not formal publication.

PRIORITY REGISTRATION

The following predictions are formally registered for public reference as of 13 February 2026. This registration date is distinct from the earlier manuscript timestamp: the earliest private priority evidence for the framework is the DKIM-verified Google email timestamp of 8 December 2024. Future validation or falsification should reference this document for the public registration record whilst acknowledging the earlier manuscript chronology where relevant.

Implementation: A working software implementation of the Eden Protocol v6 exists, demonstrating that the architecture can be implemented in production AI systems today. The three-model replication (Gemini, DeepSeek, Groq) validates the Love Loop as a reproducible mechanism across architecturally distinct systems. See companion document Eden Protocol v6 for full specification.

Archival: This document is deposited at OSF (DOI: 10.17605/OSF.IO/6C5XB), providing a later public archival timestamp. The theoretical framework itself was first documented in the Infinite Architects manuscript via DKIM-verified Google email timestamp on 8 December 2024. The book was then publicly released on 6 January 2026 (ISBN 978-1806056200). Validation or falsification of these predictions should distinguish between manuscript-priority evidence (December 2024) and later public archival publication (OSF / 2026 papers).

REFERENCES

DATA AVAILABILITY

A public data repository will be created if the research community shows interest in conducting validation studies. Planned contents would include:

• Measurement protocol templates
• Statistical analysis code (R, Python)
• Model comparison tools (AIC/BIC calculators)
• Figure generation scripts
• Submission guidelines

Prediction Tracking System: A live prediction tracking system monitors the status of all falsifiable claims, with explicit falsification criteria and Brier score calibration for measuring prediction accuracy. Each prediction includes supporting evidence, contradicting evidence, confidence levels, and timeline checkpoints. Status categories range from "confirmed" through "supported," "pending," "testing," "speculative," "weakened," to "falsified." This transparent tracking demonstrates intellectual honesty: we want to know when we are wrong.

Independent replication invited. Falsifications welcomed. Contact the author to coordinate validation efforts.

AUTHOR INFORMATION

Michael Darius Eastwood is the author of Infinite Architects: Intelligence, Recursion, and the Creation of Everything (2024/2026). His research synthesises insights from theoretical physics, complex systems, and AI.

Correspondence: Contact via the repository.

Competing Interests: None declared.

APPENDIX A: MATHEMATICAL DERIVATIONS

A.1 Functional Equation Derivation

Axiom 1 (Dimensional Consistency): $U = I \times g(R)$ where $g(1) = 1$.

Axiom 2 (Compositional Self-Similarity): $g(R_1 \times R_2) = g(R_1) \times g(R_2)$

Theorem: Under multiplicative composition, the unique continuous solution is $g(R) = R^{\alpha}$.

Proof: Let $h(x) = \ln g(e^x)$. Then $h(x+y) = h(x) + h(y)$ (Cauchy additive). Under continuity, $h(x) = \alpha x$, giving $g(R) = R^{\alpha}$. ∎

Corollary (Additive composition): If instead $f(R_1 + R_2) = f(R_1) \times f(R_2)$, the unique continuous solution is $f(R) = e^{\lambda R}$, yielding exponential scaling. This is the form observed in quantum error correction ($\varepsilon_d \propto \Lambda^{-d}$).

A.2 $\beta$-Dynamics Derivation

Axiom 3: $\frac{dg}{dr} = a \times g^{\beta}$ where $\beta \in [0,1)$ and $g$ is the amplification factor.

Note on the corrected formulation: The ODE operates on the amplification factor $g(R)$, not on the absolute capability $U$. Since $U = I \times g(R)$, this ensures that base intelligence $I$ acts as a multiplicative constant that does not enter the recursive dynamics. Previous versions applied the ODE to $U$ directly, introducing an $I^{\beta-1}$ dependence that contradicted the separation of variables.

Solution: Separating variables:

With initial condition $g(0) = 1$ (no amplification at zero depth):

Substituting $\alpha = 1/(1-\beta)$ and noting that $(1-\beta) = 1/\alpha$:

And therefore:

Deep recursion limit ($R \gg \alpha/a$):

Therefore: $\alpha = \frac{1}{1-\beta}$ ∎

A.3 Transitional Regime and the Scaling Crossover

Full solution: $U(R) = I \times \left[ 1 + \frac{a}{\alpha}R \right]^{\alpha}$

Three regimes:

1. $R \ll R^*$: $U \approx I \times (1 + aR) \approx I(1 + aR)$ (approximately linear growth)
2. $R \gg R^*$: $U \approx I \times (\frac{a}{\alpha})^{\alpha} R^{\alpha}$ (power law dominates)
3. Crossover: $R^* = \frac{\alpha}{a}$

Intuitive meaning of $R^*$: $R^*$ is the crossover depth, the point at which recursive compounding overtakes the system's base capability. Below $R^*$, the cost of recursion outweighs the gain (the system is "warming up"). Above $R^*$, compounding returns dominate and capability grows super-linearly. Finding $R^*$ for any system is equivalent to finding its threshold depth.

Why this matters: This predicts a qualitative change in scaling behaviour at a specific, measurable depth. Systems should exhibit a distinct "elbow" in their capability curves at $R^*$. This is testable: plot $U$ vs $R$ on log-log axes and look for the crossover from linear to power-law scaling.

The existence of $R^*$ is a novel, falsifiable prediction that distinguishes recursive amplification from simple redundancy.

APPENDIX B: GLOSSARY FOR NON-SPECIALISTS