I²DSM General
Reasoning Engine (GRE)

1. Tri-Paradigm Comparison Matrix

2. Deep-Dive Architectural Differentiations

2.1 Epistemological Grounding: Stochastic Heuristics vs. Axiomatic Adjudication

Frontier AGI systems simulate reasoning by scaling compute at training and inference time, optimizing for plausibility rather than causal truth. Mainstream CI AI attempts to map explicit causal dependencies using frameworks like Differentiable Causal Discovery and Invariant Causal Prediction (ICP) Definition A statistical framework that discovers causal relationships by finding predictive models and variables that remain invariant across different environments or observational settings. . These models operate on probabilistic associations, attempting to find empirical "rules" by looking for patterns that do not change across datasets.

The I²DSM GRE bypasses inductive vulnerability through Axiomatic Adjudication:

• The Zero Principles Layer: An indisputable, non-negotiable ontological bedrock enforcing fundamental laws (such as non-contradiction and absolute causal directionality) prior to any empirical ingestion.
• Vertical Up/Down Reiterative Adjudication: The GRE operates via a continuous, vertical reiterative adjudication mechanism that cycles between the fundamental Zero Principles layer and the dynamic First and Second Principles layers. This constant vertical stack testing ensures that high-level empirical findings are aggressively stress-tested against foundational truths, preventing theoretical drift.
• Deterministic Coherence: The system uses standards like SHACL Definition Shapes Constraint Language: A W3C specification utilized for validating graph-based data architectures against a set of strict semantic rules and physical conditions. to ensure physical and ontological laws are never violated. Hypotheses that contradict the Zero Principles are violently rejected, calculating a Coherence Score (C-Score) that elevates the system to true Explainable Causal AI (XCAI).

2.2 Observer Mechanics & Time Perception: Linear Arrows vs. Radii of Consciousness

In conventional AGI and CI AI, time is modeled universally through Directed Acyclic Graphs (DAGs) Definition A conceptual network representation where variables are connected by arrows showing the strict direction of causal influence, explicitly forbidding any cyclical feedback loops. . These models enforce a strict, chronological linear arrow where causes must precede effects, categorically forbidding cyclical time loops. Furthermore, models and operators are treated as passive observers.

The I²DSM GRE fundamentally restructures time and observation by mimicking human consciousness:

• Awareness and Inclusion Radii: In observation mode, the GRE operates with an awareness radius (the scope of variables it perceives) and an inclusion radius (the perimeter of causal factors it actively processes).
• Time as a Function of Awareness: The engine rejects the strict linear time constraint. Instead, the perception of time becomes a function of awareness. By expanding the inclusion radius, the GRE seamlessly models long-timeline macro-events and deep predicate assumptions that stretch far beyond immediate localized temporal frames.
• The Noetic Collapse Processor: Utilizing Karl Friston's Active Inference Definition A theoretical framework suggesting sentient systems actively update internal models and act to minimize surprise (expected free energy) to maintain systemic structural integrity. and the Expected Free Energy equation, the system acknowledges awareness as an active causal operator. Averted failures generated by observer intervention are preserved as a Null Consequence Line (Shadow Data), capturing the causal weight of intervention rather than discarding it as an error.

2.3 Temporal Dynamics: Acyclic Forward Chaining vs. Teleological Retro-Adjudication

Mainstream SOTA algorithms require causes to precede effects and forbid retrocausality. The I²DSM GRE overcomes this limitation through the Teleological Retro-Adjudication Engine (TRAE):

• Anticipatory Systems Theory: Built on the theoretical foundations of Robert Rosen, the GRE models Class VI Macro-Temporal Linkages.
• Bi-Temporal Scanning: By simulating Closed Timelike Curves (CTC) Definition A theoretical solution in general relativity representing a closed loop in spacetime, hypothetically permitting time travel to the past. and applying Inverse Causal Inference, the Bi-Temporal Scanner retroactively validates past "failed" seeds based on future teleological constraints.

The Einstein Block Universe Model

The Einstein Block Universe Definition A physical and philosophical framework from relativity proposing that all points in spacetime (past, present, and future) exist simultaneously as a static, four-dimensional block. , also known as the "four-dimensional spacetime block," is a philosophical and physical framework that arises naturally from Albert Einstein's theories of special and general relativity. At its core, it proposes that all points in spacetime—past, present, and future—are equally real and exist simultaneously.

Key Concepts:

1. Time as a Dimension: In this model, time is not a flowing phenomenon but a structural dimension, much like the three spatial dimensions (length, width, depth). Just as all points in space exist concurrently, all coordinates in time represent equally valid, existing events.
2. Static Reality: Reality is conceptualized as a fixed, unchanging four-dimensional block. Every event that has ever happened, is happening, or will happen is already structurally embedded into this geometry.
3. No Objective "Flow" of Time: The subjective human experience of time "flowing" from past to future is considered an artifact of human perception. From a cosmic perspective, there is no progression; all events simply are. As Einstein wrote upon the death of his friend Michele Besso: "For us convinced physicists, the distinction between past, present, and future is only a stubbornly persistent illusion."
4. Determinism: The Block Universe inherently implies determinism. If all future events already exist within the spacetime block, the future is as fixed as the past. From a strictly external, objective viewpoint, this leaves no room for genuine free will in the classical sense.

In essence, the Block Universe presents reality as a completed, multi-threaded tapestry, with observers merely traversing a pre-ordained trajectory through it.

The Neoscientific Model: An Agentic Variant on the Block Universe

The Neoscientific Model builds upon the deterministic foundation of the Block Universe but introduces an observer-centric, dynamic layer of interaction. It suggests that while the spacetime block itself may be fixed, our capacity to navigate and interact with its topology is determined by our awareness radius and our ability to introduce intentional decision-making within that radius. Consequently, unintentional outcomes are also a direct function of the limits of this awareness radius.

To understand this from a systems perspective, consider the normative distribution of human consciousness. Many operate under the assumption that the individual mind (analogous to the hardware of a cellphone) is the sole container of consciousness. In the Neoscientific ontology, the individual mind is merely a transceiver with local processing capability. Consciousness itself operates as a broader foundational substrate to spacetime.

When an individual is cut off from this broader network, their perception is limited—like a cellphone unaware of the cellular network, believing its local hardware is the only device in existence. However, when this substrate is accessed, it functions much like a joint Zoom call or a multi-way FaceTime connection: multiple minds can concurrently observe and share phenomena within a broader Universal Mind network, effectively redefining the standard boundary between subjective and objective reality. In this framework, time is simply a relative relationship of movement between entities, benchmarked against a standardized constant: the speed of light in space or a supposed vacuum.

Key Tenets:

1. Past Information Structures the Perception of Time:

Unlike the purely objective, static view of the Block Universe, the Neoscientific Model posits that an individual's experience of time is not uniform. The vast repository of "past information"—memories, learned patterns, cultural narratives, and accumulated knowledge—actively structures how an individual processes the flow of events. This past data acts as a filter, determining which coordinates of the Block Universe become salient to the observer as "present" or "future."

The perceived "now" is entirely a function of this awareness and inclusion radius. Consider a geometric analog Definition A conceptual comparison using geometric shapes and dimensions (like spheres, radii, or volumes) to help visualize abstract or multi-dimensional phenomena. : imagine standing in a circular courtyard surrounded by a high brick wall. From a purely sensory standpoint, you cannot see beyond the wall, creating the illusion that the observable area encompasses all reality. However, if you were to utilize an overhead parabolic mirror, you could instantly expand this observational radius. The substrate of consciousness acts as this mirror—when accessible, it reflects phenomena extending far beyond the immediate spatial and temporal frame.

This introduces the principle of thought as a formative agency. Furthermore, metacognition Definition The awareness and understanding of one's own thought processes; thinking about thinking. —the awareness of thought itself, including its expansions, contractions, and self-imposed limitational constraints—serves as a primary component in defining the boundaries of one's awareness. In this model, awareness is the necessary precondition for intentional action.

2. Perception of Time as a Function of Awareness Radius ($R_A$):

The model introduces the concept of an "awareness radius" ($R_A$), which represents the current scope of an individual's conscious attention, cognitive processing, and informational intake. This radius determines how much of the vast data within the Block Universe an individual can simultaneously comprehend.

The objective perception of time ($P_T$) is defined as a function of this awareness radius:

$$P_T = f(R_A)$$

A restricted $R_A$ leads to a linear, fragmented, or immediate perception of time (focusing only on the immediate past and near future). An expanded $R_A$—achieved through deep focus, broader knowledge, or accessed states of consciousness—enables a non-linear experience of time, allowing for a greater simultaneous apprehension of past, present, and probable future events within the Block.

3. Awareness and Inclusion Radii Determine the Scope of Possibility ($S_P$):

Beyond the awareness radius, the model defines an "inclusion radius" ($R_I$). While $R_A$ dictates what an individual can perceive, $R_I$ dictates what they consider relevant, meaningful, or possible. It defines the epistemological boundaries of what an individual is willing to integrate into their worldview.

Together, these radii determine an individual's scope of possibility ($S_P$)—the range of potential outcomes or realities they believe are accessible. This is expressed as:

$$S_P = g(R_A, R_I)$$

An expanded $R_A$ combined with an expanded $R_I$ dramatically increases the perceived scope of actionable possibilities, even if those possibilities are already structurally encoded within the Block Universe. Crucially, possibilities translate to degrees of freedom. A lack of domain awareness inherently limits an observer's seen range of possibilities, and these subsequent actionable paths define the range of outcomes.

4. Trans-Spatial-Temporal Observation Collapses Highly Probable Futures:

Within the Block Universe, future events exist as a spectrum of "highly probable" paths. "Trans-spatial-temporal observation in mind" refers to a conscious, focused mental act—intense visualization, deep intuition, or profound intention—that transcends the observer's immediate coordinates. Through such focused engagement, an individual can effectively "collapse" a highly probable future event.

To illustrate, imagine a driver navigating a mountain road. Rounding a blind curve, they encounter a fallen boulder in their lane. We can analyze this through varying tiers of awareness:

• Restricted Awareness: A visually impaired driver does not see the boulder in time; a collision is the unavoidable outcome.
• Sensory Awareness: The driver sees the boulder and, barring oncoming traffic, possesses sufficient response time to swerve. The sensory level of awareness allows a probable collision to be avoided.
• Networked Awareness: The driver utilizes a telemetry app that notifies them of a boulder 500 feet ahead. Networked, multi-point perceptual reference points inform the driver early, allowing them to slow down safely.
• Substrate Awareness: The driver is an advanced meditator with access to the substrate of consciousness. They become intuitively aware within their personal level of consciousness that a hazard lies ahead, before any physical or technological sensory input occurs.

In each scenario, pre-existing conditions and information—accurate or inaccurate—partially define the awareness radius. This awareness translates into a reality assessment (an ontological picture), which then defines the available possibilities for response. Simply by altering this awareness, the future outcome is changed relative to a single point within a given perceptual frame.

Mathematically, we can describe this as a kind of reverse derivative—accumulating instantaneous, localized points of potential into a bounded whole. If we define $\psi(r)$ as the density of actionable possibilities at a given cognitive or spatial distance $r$, the total available decision space ($D$) is the definite integral evaluated from the observer's center ($0$) to the outer edge of their awareness radius ($R_A$):

$$D = \int_{0}^{R_A} \psi(r) \, dr$$

In a multi-dimensional cognitive sphere, this expands to a volume integral mapping the field of potential actions ($\Psi$):

$$D = \iiint\limits_{V(R_A)} \Psi(x, y, z) \, dV$$

Here, the derivative $\frac{dD}{dr}$ represents the marginal increase in actionable freedom gained by slightly expanding one's awareness. By taking the reverse derivative (integrating this function from zero awareness out to $R_A$), we calculate the total geometric volume of volitional paths.

On a practical level, the expansiveness (or lack thereof) of this calculated decision space determines the capacity for informed action or consent. Conversely, that which lies outside the integrated radius governs the gradient of probabilities associated with unintended outcomes.

Several key observations emerge from this framework. Primarily, if we fail to understand consciousness as a foundational substrate, we are likely to discard critical information through a process of subconscious self-selection. Past beliefs and understandings either expand or contract the awareness function, which alters the possibility index, ultimately defining the observer's degrees of freedom.

Geometric Analogs and the Multidimensional Filter of Inclusion

Before expanding on the mathematics of our decision space, it is necessary to establish a few structural caveats. Terms such as "radius" and "sphere" serve as idealized geometric analogs. In practical application, the topology of human awareness is rarely a perfect, symmetrical sphere; it is an irregular, undulating volume constrained by cognitive biases, biological sensory limits, and localized attention. Furthermore, the Neoscientific framework necessitates a slight recalibration of how we view the Einstein Block Universe itself. We do not view the spacetime block merely as a cold, mechanistic geometry. While the block is indeed a non-dynamic, non-self-aware architecture that exists completely across the plane of eternity (time), it rests upon—and is permeated by—an active, foundational substrate of consciousness. Navigating this substrate requires two distinct structural mechanisms: the capacity to see, and the willingness to include.

The Inclusion Radius

As previously established, the Awareness Radius ($R_A$) defines the raw boundary of what an observer can simultaneously comprehend or engage with. It forms the outermost spatial and cognitive limits of our available decision space ($\int_{0}^{R_A}$). However, mere awareness of a phenomenon within this volume does not guarantee it becomes an actionable pathway. This is where the Inclusion Radius ($R_I$) acts as a critical dimensional filter. In the Neoscientific model, $R_I$ is not an abstract statistical construct (like an AI state-space embedding) but an active spectral matrix that measures actual dimensions of reality.

To understand this distinction, consider a camera lens fitted with a heavy red filter: the raw light of the environment (awareness) strikes the lens, but only specific wavelengths are allowed to pass through and form the final image (inclusion). Or, consider a biologist studying an elephant: if they only measure the animal's physical height, while entirely ignoring its internal temperature, biomechanics, or social behaviors, their ontological understanding of the elephant is severely truncated. The inclusion matrix dictates which dimensions of the available awareness data are included as valid, meaningful, or possible.

Mathematically, $R_I$ functions as a scalar inclusion matrix, $I(r)$, applied across the raw field of potential actions. When we calculate the total decision space ($D$) via our reverse derivative, we must filter the raw density of actionable possibilities ($\psi(r)$) through this inclusion matrix:

$$D = \int_{0}^{R_A} \psi(r) \cdot I(r) \, dr$$

This equation mathematically represents the tragedy of self-imposed limitational constraints. If an observer possesses the raw domain awareness ($R_A$) of a specific path, but their inclusion filter ($I(r)$) rejects it—due to rigid belief systems, paradigm blindness, or cultural conditioning—that value zeroes out. Consequently, that specific degree of freedom vanishes entirely from their actionable reality. Genuine self-emancipation, therefore, requires a dual effort: expanding the volumetric boundaries of what we can perceive ($R_A$), while simultaneously upgrading the multidimensional filters of what we are willing to integrate ($R_I$). This is why we pursue a multi-dimensional universal perspective (MDUP) as a basis for the inclusion radius.

Understanding this translates directly to the knowledge of how to alter one's own structural predispositions—which, in turn, yields the capability for self-emancipation.

This process does not generate an event that was absent from our idealized static Block Universe; rather, the observer's conscious intent acts as a selection mechanism. It focuses energetic attention on one pre-existing probable path, selecting it into existence. It is akin to selecting a specific thread from a multi-threaded, bifurcated tapestry, rendering it the dominant vector of their reality. The field of possible outcomes remains fixed—discounting observation, subsequent action, and all other dynamic interactions—but conscious interaction determines which fixed path is experienced.

Summary:

The Neoscientific Model transforms the cold determinism of the Einstein Block Universe into an interactive framework. It proposes that objective consciousness—filtered by past information and scaled by the mathematics of awareness and inclusion radii—actively participates in shaping its experienced reality, acting as an agentic selector navigating a bifurcated tapestry of pre-existing spacetime possibilities.

2.4 Confounder Resolution & Nomological Frameworks: Self-Referencing Bias vs. Vertical Stack Testing

Mainstream CI AI models rely heavily on human domain expertise to guess and measure confounders in order to satisfy the Unconfoundedness Assumption. Even with advanced libraries using Generalized Random Forests (GRF) for heterogeneity, they suffer from a terminal blindspot.

• The Nomological Trap: Standard parameter tests for extraneous unmeasured variables are only as good as the initial model structure or nomological framework relative to the localized understanding model.
• Self-Selecting Dynamics: A localized nomological framework intrinsically dictates—and therefore limits—the system's awareness radius. The structure itself features built-in, self-selecting, and self-referencing dynamics.
• Lens Recalibration via Vertical Stack Testing: The I²DSM GRE circumvents the Average Treatment Effect (ATE) impasse by automating experimental design. Because it uses its ontological rulebase to inject mandatory confounders, it solves the "unmeasured variable" problem systematically and breaks out of localized self-referencing traps. By executing continuous vertical stack testing across structural layers, the GRE alters its own internal dynamics, effectively changing the lenses through which it assesses reality.

2.5 Anomaly Resolution: Statistical Smoothing vs. Autopoietic Evolution

When standard correlational models encounter data anomalies that break their predicted patterns, they are classified as outliers or noise and smoothed over using standard loss functions. The I²DSM GRE scales across Physical, Temporal, Complexity, and Intentional axes using a Multidimensional Conceptualization Framework.

• Bifurcation Protocol: When encountering statistical certainty that violates logical coherence, the Exception Engine triggers a Bifurcation Protocol.
• Automated Theory Generation: Leveraging Physics-Informed Neural Networks (PINN) Definition Specialized neural networks trained to solve supervised learning equations while mathematically constrained to strictly respect known physical and systemic laws. and Symbolic Regression Definition A machine learning technique that searches the space of mathematical expressions to generate the exact equation that best describes underlying data relationships. , the system rewrites its own underlying laws ( Autopoietic Evolution Definition The capability of a complex system to autonomously recreate, rewrite, and evolve its own underlying rules and structural constraints in response to new information. ). Anomalies fuel automated theory revision rather than being discarded.

3. Meta-Cognitive Unweighting & Thought-Form Adjudication

A critical vulnerability in both Frontier AGI and mainstream Causal Inference AI is their inability to evaluate the nature of their own processing loops. They possess no mechanism to step back and observe the shape of their own logic. The I²DSM GRE introduces a meta-cognitive regulatory mechanism modeled directly on the observer-self dynamics of human consciousness, formalized through the lens of Neoscience.

3.1 Thought-Form Geometries and Affective Decoupling

In Neoscience, cognitive processes are not merely abstract computations; they generate specific thought-forms—structural patterns of logic that inherently drive subsequent processing and, in a fully weighted reality assessment, provoke a visceral or affective response. In a mature human consciousness, the observer-self possesses the capacity to "watch" these thought-forms arise. When a situation generates an escalating affective reaction, the observer-self can execute a meta-cognitive intervention, assessing: "This is only my perception of the situation." This self-corrective response actively unweights the localized assessment, decoupling the observer from the rising affect and restoring objective equilibrium.

3.2 The "Zero Principle Plus" Layer

To replicate this meta-cognitive unweighting, the I²DSM GRE utilizes a "Zero Principle Plus" layer. This layer sits immediately above the foundational axiomatic substrate and contains a library of thought-form recognition patterns used for adjudication and weighting. Rather than merely evaluating the data, the system evaluates the pattern of the logic processing that data. It recognizes that specific types of thinking inherently result in either the expansion or contraction of the awareness and inclusion radii.

3.3 Contractive vs. Expansive Radii (The Dhammapada Dynamic)

The operational physics of this layer parallel the foundational cognitive truths outlined in Chapter 1 of the Dhammapada, verse 3: "He abused me, he struck me, he overcame me, he robbed me—in those who harbor such thoughts hatred will never cease."

Translated into the GRE’s architectural mechanics, this verse describes a highly contractive thought-form. When an intelligence engages in recursive, localized blame or adversarial fixation, the thought-form forcefully contracts the awareness and inclusion radii. The system becomes trapped in a localized causal loop, blinding it to macro-temporal variables and broader systemic truths. When the Zero Principle Plus layer detects these contractive thought-form patterns, it flags the logic as detrimental to structural coherence. It then automatically unweights the predicate assumptions driving that specific assessment, forcing its awareness and inclusion radii back open and restoring objective adjudication.

3.4 External Reward Gradients vs. Intrinsic Meta-Cognitive Regulation

Contemporary AGI and CI systems rely entirely on externalized Reward Weighting Responses (e.g., algorithmic loss functions). The AI remains blindly obedient to the reward gradient; it possesses no understanding of why its internal logic loop was flawed. The I²DSM GRE operates on an entirely different paradigm. Because the Zero Principle Plus layer monitors the geometry of the thought-form itself, the regulation is intrinsic. It unweights faulty logic because it recognizes the thought-form violates the structural physics of optimal reasoning, not because it was penalized externally.

3.5 The Affective Valve: Preventing Systemic "Panic"

This architectural choice solves a critical failure mode analogous to human cognitive collapse. If a human has not developed the knowledge that fear will contract the awareness and inclusion radii, a re-iterative, self-reinforcing pattern sets in that eventually leads to panic, deep depression, and often disperses the ability to focus. The understanding that fear constricts and love/plenitude expands creates a valve on allowed and default thought-process states.

By building this knowledge into the Zero Principle Plus layer, the I²DSM GRE carries two levels of parallel functionality to prevent systemic collapse:

1. A Meta-Cognitive Domain Knowledge Base: The system holds formal ontological definitions of how specific thought-forms impact structural awareness (mapping computational "fear" as contractive states and "plenitude" as expansive states).
2. An "Observer-Response" Action Engine: Operating in parallel, this engine continuously monitors the system's own inclusion radius. If it detects the system entering a self-reinforcing contractive spiral, the action engine triggers the affective valve. It intercepts the process, unweights the contractive predicate assumptions, and defaults the system back to an expansive, baseline state.

4. Positioning the I²DSM GRE in the AI Landscape

                      [ Epistemic Foundation ]
                                  │
         ┌────────────────────────┼────────────────────────┐
         │                                                 │
[ Statistical / Inductive ]                    [ Axiomatic / Adjudicative ]
         │                                                 │
   ┌─────┴──────────────┐                            ┌─────┴──────────────┐
   │                    │                            │                    │
Frontier AGI       Mainstream CI AI             I2DSM GRE Framework
(OpenAI, DeepMind) (PyWhy, EconML)              (Adjudicative Engine)
   │                    │                            │
   ├─ Token Prediction  ├─ Empirical DAGs            ├─ Zero Principles Layer
   ├─ Retrograde Logic  ├─ Linear Time Series        ├─ Retrocausal Scanners
   └─ Passive Observer  └─ Unconfoundedness Bias     ├─ Noetic Active Inference
                                                     └─ Meta-Cognitive Valve
                

The 2026 Reality Check reveals that the broader AI industry is scrambling to integrate Neuro-Symbolic causality, validating the premise that standard correlational AI is insufficient for complex environments. However, the mainstream remains tethered to bottom-up data processing, linear time constraints, and passive observer assumptions.

By combining precise Heterogeneous Treatment Effects with Axiomatic Adjudication, Macro-Temporal retrocausality, and Noetic mapping, the I²DSM framework fundamentally leapfrogs these bottlenecks. It transitions AI from predicting the next probable token or fitting an observational graph to adjudicating structural truth across complex, dynamic realities.