Purpose & architecture
A separate, dependency-free JavaScript reference links each exported operation to sections of the mathematical specification. Its modules cover sixteen family transforms, a seventeen-component meta-state, the Omega objective, DNA memory, Gate5000, neural dynamics, a lattice and federation cross-talk. The documentation preserves the source formulas and their author explanations. This generation can be studied in a browser or Node without treating it as the later distributed MEGAMIND runtime.
The source header describes fidelity to sixty-nine equations; the present catalogue retains individual expressions and variants instead of repeating that count as an independently verified total. Several document explanations are hypotheses or analogies, and mathematical errors identified by review remain visible beside the originals.
This source generation
This record follows the main branch of Janady13/seferim-core at commit 1f05cd5640edf0a5fe93dc276a12a48db84fc702. The snapshot identifies the source inspected in this audit. It is not a statement about which revision is currently running on a device.
| Field | Source record |
|---|---|
| Revision | 1f05cd5640edf0a5fe93dc276a12a48db84fc702 |
| Branch | main |
| Recorded generation | Mathematical reference v1.0.0 |
Recovered implementation structure
These paths locate the components and entry points represented by this build. The source register contains their inspected revisions.
- README.md
- docs/FOUNDATIONS.md
- docs/MATHEMATICS.md
- examples/quickstart.js
- package.json
- site/index.html
- src/seferim-core.js
- test/run.js
Behavior & verification limits
The source header describes fidelity to sixty-nine equations; the present catalogue retains individual expressions and variants instead of repeating that count as an independently verified total. Several document explanations are hypotheses or analogies, and mathematical errors identified by review remain visible beside the originals.
Original project documentation
The following documentation is preserved as a dated source account. Claims in it retain the source’s wording and must be read alongside the implementation notes above.
SEFERIM AGI — ThatAIGuyCore
The G¹⁶ Federation: a golden-ratio, 16-dimensional dynamical-systems substrate for artificial cognition
    
SEFERIM is a clean-room, zero-dependency reference implementation of ThatAIGuyCore — a unified mathematical framework that treats cognition as the evolution of a 16-dimensional meta-state under sixteen coupled "cognitive families," all governed by the golden ratio φ. It is a substrate: a small, fully-deterministic engine for golden-ratio dynamical systems, holographic memory, and federated multi-agent coherence.
📖 Full interactive documentation, live demos, and the complete mathematical reference: thataiguy.org/core
This repository implements all 69 documented equations of the ThatAIGuyCore v1.0.0 specification verbatim — every function in [src/seferim-core.js](src/seferim-core.js) cites the spec section (§) it implements, and [test/run.js](test/run.js) verifies the math (including the canonical FNV‑1a test vectors).
Install
npm install seferim-coreOr load it straight in the browser as an ES module (no build step):
<script type="module">
import { MetaState, DNAMemory } from "https://cdn.jsdelivr.net/npm/seferim-core/src/seferim-core.js";
</script>Quick start
import { MetaState, DNAMemory, NeuralBrain, PHI } from "seferim-core";
// 1. A single-stack cognitive core: 16 families + golden normalization.
const mind = new MetaState({ init: new Array(16).fill(0.1) });
const out = mind.step({ dx_norm: 0.3, ed_error: 0.1, utility: 0.6, stability: 0.8 });
console.log(out.state, "Ω =", out.omega); // 16-D meta-state + objective (free-energy-style)
// 2. Holographic memory — knowledge smeared across 16 golden bases.
const mem = new DNAMemory();
mem.learn("rhythm").learn("groove").learn("pocket");
console.log(mem.queryNorm("groove")); // correlation recall in [0,1]
// 3. An 88-agent neural brain (dna_v9 dynamics).
const brain = new NeuralBrain();
for (let i = 0; i < 100; i++) brain.step(0.6);
console.log(brain.consciousness(), brain.synchrony());npm test # 42 assertions: constants, FNV-1a vectors, every family, all enginesThe 13 systems (G¹⁶)
| # | System | What it does |
|---|---|---|
| 1 | Fundamental constants | φ, δ (DNA increment), τ |
| 2 | Golden basis | ψ_k(x) = sin(2πφ^k x) + cos(2πφ^k x), normalization, spiral angles |
| 3 | The 16 families | continuous/discrete dynamics, reaction-diffusion, optimization, Bayesian, learning, mutual-information, rate-distortion, consensus, swarm, field accumulator, free-energy, compression, memory-trace (Zecher), policy, global coherence (Kehillah) |
| 4 | Meta-state core | weighted family application → φ-correction (inertial blend) → stability gating → golden normalization |
| 5 | Objective Ω | Surprise + Uncertainty − Value + Penalty (a free-energy-style functional) |
| 6 | DNA holographic memory | golden-basis encode/recall + cosine coherence |
| 7 | Gate5000 | 5,000-gate XOR binary substrate driven by two quasi-periodic phases |
| 8 | Neural brain (dna_v9) | 88 agents with velocity, drive, gating, potential, coupling → consciousness & synchrony |
| 9 | Consciousness engine | 174 core + 200 supplemental equations → a 374-D binding field |
| 10 | Lattice engine | 16 strands, golden rotation kernels, Hebbian plasticity |
| 11 | Federation cross-talk | coupled consciousness signals across agents (decay + coherence-weighted coupling) |
| 12–13 | Activations & hashing | softsign, sigmoid, clamp; FNV-1a |
Built on real mathematics (honestly)
The framework synthesizes established theory — the Free Energy Principle (Friston), information theory (Shannon; Cover & Thomas), holographic / vector-symbolic memory, Hebbian plasticity, swarm consensus (Vicsek / Cucker–Smale), and golden-ratio harmonics. Full citations are in [docs/FOUNDATIONS.md](docs/FOUNDATIONS.md).
We document the lineage precisely rather than overclaim. In particular: - δ = 0.013618 is an empirical quasi-periodic phase increment — not 1/φ³ (which is ≈ 0.236). - The memory system is a golden-ratio frequency-domain Vector Symbolic Architecture, inspired by — not a literal implementation of — Plate's circular-convolution Holographic Reduced Representations. - The mutual-information (Family 6) and rate-distortion (Family 7) updates are information-theory-inspired one-step rules, not exact estimators/solvers.
Documents
- [
docs/MATHEMATICS.md](docs/MATHEMATICS.md) — the complete 69-equation reference (the spec this code implements). - [
docs/FOUNDATIONS.md](docs/FOUNDATIONS.md) — cited mathematical foundations for every component.
About
SEFERIM / ThatAIGuyCore is the cognitive-substrate research of Joseph W. Anady (ThatAIGuy.org). Interactive docs + live demos at thataiguy.org/core.
Attribution & provenance
SEFERIM / ThatAIGuyCore is the original work of Joseph W. Anady (ORCID 0009-0008-8625-949X). Authorship and priority are established by a permanent, timestamped public record:
- Archived & dated (DOI): 10.5281/zenodo.20564321
- Public commit history: this repository
- ORCID: 0009-0008-8625-949X
Use is welcome under the MIT License, which requires retaining the copyright notice (see [LICENSE](LICENSE) and [NOTICE](NOTICE)). Derivative works must preserve this attribution and must not present SEFERIM / ThatAIGuyCore, or this framework, as their own original creation. Forks must be renamed and must credit this origin and DOI.
Cite
Anady, J. W. (2026). SEFERIM / ThatAIGuyCore: A Golden-Ratio, 16-Dimensional Dynamical-Systems Framework for Artificial Cognition (v1.0.0). Zenodo. https://doi.org/10.5281/zenodo.20564321
- DOI: 10.5281/zenodo.20564321
- OSF project: https://osf.io/8e9ks/
- ORCID: 0009-0008-8625-949X
License
MIT © 2026 Joseph W. Anady / ThatAIGuy.org
Equations in this build
94 linked mathematical records. Each opens its notation, interpretation and source.
5a. FNV-1a 32-bit hash (input → basis index / h(item))
This relation defines hash ← offset_basis for byte in input: hash ← (hash XOR byte) hash ← (hash × prime in the source section “5a. FNV-1a 32-bit hash (input → basis index…
Golden ratio: the positive root of a quadratic
The golden ratio is the positive solution of φ²=φ+1. The identities φ−1=1/φ and 1+φ=φ² explain several equivalent constants elsewhere in this project. It is a fixed dimensionless…
DNA phase increment: the declared decimal constant
This version advances its DNA phase by 0.013618 of a turn per update. The document’s nearby approximation δ≈1/φ³ is numerically incorrect: 1/φ³≈0.2360679775. The written decimal…
Locally defined tau: reciprocal angular scale
Here τ is defined to be 1/(2π), approximately 0.159154943. Multiplying an angle in radians by this constant converts it into a fraction of a full turn. This local notation must be…
Golden-frequency trigonometric feature
For each index k, this function maps the scalar x to sin(a)+cos(a), where a=2πφᵏx. The two terms combine into √2 sin(a+π/4), so each component has amplitude √2 and range [−√2,√2].…
Norm-dependent state contraction
The multiplier b decreases as the squared Euclidean norm of Ψ grows: b=1 at the zero vector and approaches zero as the norm becomes large. If b is computed from the same vector it…
Reciprocal golden sequence of angles
The angle at index k is a full turn divided by φᵏ. Successive angles shrink by the factor 1/φ. This sequence differs from the angle θₖ=2πk/φ used in this document’s kernel…
Continuous family: ten-percent target relaxation
The update is 0.9x+0.1d, with d=dx_norm. It retains 90% of the previous scalar state and moves 10% toward the supplied target. For a fixed d, the error after n updates is…
Continuous-time state equation
The derivative x′ is the instantaneous rate of change, and F specifies how that rate depends on state and time. An Euler approximation would use x_next=x+dt·F(x,t). The…
Discrete family: utility smoothing
This family forms a weighted average of the current state and utility, with weights 0.9 and 0.1. A constant utility u is a stable fixed point, and deviations from it shrink by a…
General discrete state transition
F maps a current state and input to the next state. This is the general form of a driven discrete dynamical system. Reproduction requires the actual mapping, initial state, and…
Reaction-diffusion family: scalar softsign relaxation
The actual scalar update is 0.95x+0.05 softsign(dx_norm). It smooths a bounded transform of the input, approaching that transform when the input is constant. No spatial neighbors,…
Reaction-diffusion equation used as an analogy
The Laplacian ∇²x describes spatial diffusion and f(x) describes a local reaction. A numerical implementation must represent neighboring spatial positions and specify boundary…
Optimization family: bounded movement toward utility
The state moves in the direction of utility−x, with step magnitude 0.2|utility−x|/(1+|utility−x|). For a fixed utility, the error is multiplied by 1−0.2/(1+|error|), which lies…
Utility maximizer used as an analogy
The argmax expression denotes an input that achieves the largest utility, assuming a maximizer exists. It does not itself specify a gradient method, a step size, or a unique…
Bayesian family: scaled and clipped utility update
The numerator adds utility to the current state, the denominator attenuates that sum by 1+|utility|, and the final clamp restricts the output to [0,1]. For nonnegative utility,…
Bayes’ rule used as an analogy
The posterior is proportional to the likelihood times the prior, with the evidence providing normalization. This formula updates a distribution over hypotheses using observed…
Learning family: additive input accumulation
Each application adds one tenth of dx_norm to the current scalar. With a fixed input d, the isolated recurrence has the exact solution xₙ=x₀+0.1nd. This can serve as an update…
General additive weight update
A stored weight matrix is changed by an increment ΔW. This equation is bookkeeping common to many learning rules; the content of learning comes from how that increment is computed…
Mutual-information family: sigmoid smoothing
The output averages the current state and the logistic transform of dx_norm. A constant input drives the state toward σ(dx_norm), and deviations halve on each update. This…
Rate-distortion family: utility-minus-error increment
The net change is 0.05 times utility minus ed_error. Positive utility exceeding error increases the state; equal values leave it unchanged. The formula is a scalar control rule…
Consensus family: five-percent input averaging
The next state keeps 95% of x and incorporates 5% of dx_norm. It converges to a constant input with error factor 0.95 per update. It becomes a network consensus mechanism only if…
Neighbor-difference consensus expression
Each agent adds a sum of differences between neighbor states and its own state. Coupling weights, the neighbor graph, and step-size restrictions determine whether agents converge…
Swarm family: bounded scalar attraction
The increment is 0.05 softsign(dx_norm−x), so its magnitude is less than 0.05 and its direction points toward the input. For a fixed target, this reduces the distance to that…
Pairwise swarm interaction expression
The function f converts a relative displacement into a pairwise contribution, and the sum aggregates contributions from other agents. To interpret the displayed result as motion,…
Field accumulator: golden-ratio exponential averaging
The mixing coefficient ρ=1/(1+φ)=1/φ²≈0.381966. Each update retains about 61.8% of the old state and takes about 38.2% of dx_norm. This is an exponential moving average: with a…
Leaky accumulator reference equation
The old stored quantity is multiplied by 1−ρ and a new increment is added. When 0<ρ≤1, earlier contributions decay geometrically. This reference uses an arbitrary increment Δφ,…
Free-energy family: magnitude penalty plus utility
The state receives the increment 0.05(utility−|dx_norm|). The absolute-value term penalizes input magnitude regardless of its sign, while utility contributes with its sign intact.…
Variational free-energy reference expression
The expectation is taken under a variational distribution q(z); the integrand compares its log density with the joint generative density p(x,z). Under proper normalization, this…
Compression family: monotone magnitude subtraction
This rule subtracts 0.05 times the absolute input. Applied in isolation, it never increases x and can decrease it without bound under a persistently nonzero input. It supplies a…
Memory family: additive trace accumulation
The update stores an increment equal to 0.02 times the sum of normalized input and utility. Repeated updates accumulate their history in a single scalar, so different histories…
Unresolved memory-trace analogy
The source suggests combining indexed functions over a differential quantity dΩ, but the displayed sum-and-colon notation does not define an integration domain or measure. It is a…
Policy family: bounded utility drive and error cost
Utility first passes through softsign, making its contribution lie strictly between −0.15 and 0.15; the error term is then subtracted linearly. The combined increment can…
Coherence family: slow stability tracking
The mixing coefficient is 0.01(φ−1)≈0.00618034. The state takes a little over six tenths of one percent of the gap to the supplied stability value on each update. A fixed…
Two-state master recurrence
The next state depends on both the current state and the previous state, together with external inputs. This notation summarizes the family update, blending, gating, and…
Apply each family rule and its weight
Each component first passes through its own family function and is then multiplied by its scalar weight. The family index chooses the update law, while the weight changes its…
Blend family output with the two-state interpolant
Half the result comes from the weighted family update. The other half is an interpolant between the previous and current states, with weights 2−φ and φ−1; these weights are…
Stability-controlled update fraction
The stability input is clipped to [0,1] and mapped to a gate between γ_min and 1. The next intermediate state takes the fraction γ of the gap from the current state to the…
Apply the final state scale
Every intermediate component is multiplied by the shared normalization factor b(t+1). A shared positive multiplier preserves component signs and relative proportions but reduces…
Composite objective: change, activity, utility, and penalty
The objective adds the project’s surprise, uncertainty, and penalty terms and subtracts value. If the system minimizes Ω, it therefore favors smaller changes and penalties and…
State-change cost using two norms
The first term measures average absolute component change and the second measures the sum of squared changes. With positive coefficients, both are nonnegative. For a fixed total…
Activity-derived uncertainty score
Because b decreases with state norm, 1−b² increases from zero toward one as that norm grows. It is therefore a monotone transform of activity magnitude in this version. It does…
Utility multiplied by a weighted state sum
The inner product adds wᵢΨᵢ over the selected components, and utility scales that total. Aligned signs of weights and states increase the inner product; opposing signs can make it…
Quadratic input penalty
Squaring dx_norm makes equal positive and negative inputs incur the same cost. For λ≥0, the penalty is nonnegative and grows quadratically, so doubling input magnitude quadruples…
Update a coefficient from a hashed feature
This exponential update blends the old coefficient with a weighted trigonometric feature of the item’s hash. The importance score multiplies the new contribution, while α sets how…
Query by a sixteen-feature inner product
The query is hashed into the same scalar domain, expanded into sixteen basis values, and compared with the stored coefficient vector using a dot product. Contributions with…
Affine rescaling of a query score
Dividing by 32 and adding one half maps a score of −16 to 0, zero to 0.5, and 16 to 1. That operation guarantees a [0,1] result only if K is already bounded within [−16,16]. The…
Unity-centered scalar score Φ(x)
The score is largest at x=1 and decreases symmetrically as x moves away from 1. It is continuous, positive for finite real x, and at most 1, with a sharp derivative change at x=1.…
Cosine similarity between coefficient vectors
The dot product divided by both vector lengths measures directional alignment, producing a value in [−1,1] for nonzero real vectors. A value of 1 means positive collinearity,…
Advance the DNA phase modulo one
Adding δ advances phase by a fixed fraction of a turn and reduction modulo one wraps it into [0,1). For the exact decimal δ=0.013618, the phase returns after 500000 increments…
Advance phase by the reciprocal golden ratio
This is a rotation of the unit circle by 1/φ per update. In exact real arithmetic the irrational increment prevents an exact return after a positive integer number of steps. An…
Arithmetic average of two wrapped phases
The bias is the ordinary mean of two numbers in [0,1), so it also lies in that interval. Because phases wrap at one turn, this average is sensitive to the chosen cut: phases 0.99…
Deterministic threshold mask and XOR gate update
A gate flips when its index modulo 1000 falls below the threshold 1000×bias. The next bit is the XOR of its old value, its input bit, and that deterministic mask bit. With five…
Input with additive Gaussian noise
The incoming scalar is perturbed by a Gaussian draw. The accompanying document identifies 0.1 as the standard deviation, so the intended perturbation has mean zero and variance…
Shift a forty-four-value history buffer
Each existing entry moves one slot toward the beginning of the buffer and the current x is inserted at the final slot. This keeps the most recent forty-four samples in order after…
Leaky accumulator of delayed displacement
The update is y_new=0.99y_old+x−x_old. It retains most of the previous y and adds a displacement measured against the history value called x_old. When that value is the oldest…
Combine input, velocity-like state, and coupling
The drive combines three terms: input is attenuated by 1−x, the velocity-like state contributes with weight 1.2, and coupling state c contributes with weight 0.6. If x is near…
Sigmoid gate with an added floor
Potential P and coupling parameter k_c set the sigmoid argument, and adding 0.05 creates a positive floor. For finite inputs, the gate lies strictly between 0.05 and 1.05, so it…
Activation update with restoring drift and clipping
The change combines gated drive with a small restoring term toward x=0.5. A step of size 0.01 is then applied and projected onto [0,1]. This guarantees a bounded activation after…
Potential update with decay and quadratic damping
The potential retains 95% of its old value, receives the product F_in y, and loses 0.01P². The clamp then bounds the stored result between zero and one. The product can inject or…
Coupling-state recurrence
Expanding the increment gives c_new=[1+0.01(0.8P−k_c)]c+0.01(0.8P+k_c). For fixed P and k_c, this is an affine scalar recurrence whose stability depends on the magnitude of its…
Average potential of eighty-eight units
The aggregate adds the eighty-eight potential values and divides by their count. Because each P is clipped to [0,1], their arithmetic mean also lies in [0,1]. The source calls…
Mean cosine phase projection
This score averages cos(k_m,i), producing a value in [−1,1]. It measures phase alignment with the chosen zero-angle axis: perfectly aligned phases at zero give 1, while perfectly…
Generate one hundred seventy-four indexed core values
Starting from the declared seed core_eq[−1]=0.5, each indexed value is 0.5 plus a sine-modulated half of the preceding value. By induction, every value stays in [0,1], since the…
Generate two hundred cosine-modulated supplements
Each supplemental value reuses a core value selected by i modulo 174 and multiplies it by a cosine envelope. The cosine can be negative, so the supplements can lie below zero even…
Average the three hundred seventy-four binding components
This expression returns the arithmetic mean of the binding_field array. Its interpretation and range depend on how the 174 core and 200 supplemental values enter that array and…
Diagonal-plus-cyclic kernel matrix
The matrix places cos(θₖ) on its diagonal and 0.1sin(θₖ) on a cyclic neighbor diagonal, with zeros elsewhere. Multiplication combines each component with its cyclic neighbor.…
Euler relaxation under a kernel and core input
The matrix first transforms the state. The stored state then moves by dt times the difference between that transformed, externally driven value and its current value. This is a…
Euclidean magnitude of a strand state
Squaring each component, summing, and taking a square root gives the Euclidean norm. It is nonnegative, equals zero only for the zero vector, and scales linearly with the absolute…
Local score that decreases with state magnitude
This reciprocal transform assigns score one to zero state magnitude and approaches zero as magnitude grows. A magnitude equal to φ produces a score of one half. The equation…
Mean of sixteen local lattice scores
The global value is the arithmetic mean of the sixteen local scores. If each local value is in (0,1], the mean is also in that range. Averaging summarizes the marginal scores, but…
Hebbian outer-product weight increment
The product of two state components changes their connection: equal signs increase it and opposite signs decrease it when η is positive. Clipping after addition keeps each stored…
Coupled federation-state differential equation
Each agent loses activity at rate λSᵢ and receives weighted, bounded tanh contributions from other agents, modulated by their pairwise score. The decay competes with the network…
Euler step followed by bounded projection
The first line advances an agent state by dt times its current derivative estimate. The second clips that proposal into [0,1]. This makes every stored scalar bounded for finite…
Mean pairwise federation similarity
There are n(n−1)/2 unordered pairs among n agents, so multiplying their sum by 2/[n(n−1)] yields the mean pairwise cosine similarity. For valid cosine inputs the result lies in…
Softsign bounded activation
Dividing x by 1+|x| preserves its sign and maps finite real inputs into (−1,1). Near zero it is approximately x; large magnitudes approach saturation gradually. It has a…
Logistic sigmoid
The sigmoid maps every finite real input to (0,1), gives 0.5 at zero, and increases monotonically. Its derivative is σ(x)(1−σ(x)), with maximum slope one quarter at zero.…
Projection onto the unit interval
Inputs below zero become zero, inputs above one become one, and values already inside [0,1] remain unchanged. The map is continuous and nonexpansive, but it has derivative changes…
Two-component Euclidean norm
The square root of a²+b² is the length of the vector (a,b). It obeys the triangle inequality and is zero only when both components are zero. Despite the local name smooth_norm,…
FNV-1a thirty-two-bit string hash
The algorithm starts from a fixed offset, XORs each input byte into the state, and multiplies by a fixed prime with reduction modulo 2³². Processing bytes in order yields a…
Scale a thirty-two-bit hash to a scalar
Dividing an unsigned 32-bit hash by its maximum possible value maps it into [0,1]. The result has only 2³² possible exact values before floating-point rounding, including both…
seferim-core · § 2.1 golden basis function ψ_k(x)
This relation defines § 2.1 golden basis function ψ_k(x) in the source section “seferim-core · § 2.1 golden basis function ψ_k(x)”. Evaluates oscillatory sine or cosine terms…
seferim-core · § 2.2 normalization b(t)
This relation defines § 2.2 normalization b(t) in the source section “seferim-core · § 2.2 normalization b(t)”. It specifies the displayed relationship between the named…
seferim-core · § 2.3 golden spiral rotation θ_k
This relation defines § 2.3 golden spiral rotation θ_k in the source section “seferim-core · § 2.3 golden spiral rotation θ_k”. It specifies the displayed relationship between…
seferim-core · § 5. Objective Ω
This relation defines § 5. Objective Ω in the source section “seferim-core · § 5. Objective Ω”. It specifies the displayed relationship between the named quantities or parameters.…
seferim-core
This relation defines § 6.1 θ_k ← (1−α)θ_k + α·w·ψ_k(h(item))·Φ(importance) in the source section “seferim-core”. It specifies the displayed relationship between the named…
seferim-core · § 6.2 K(query)
This relation defines § 6.2 K(query) in the source section “seferim-core · § 6.2 K(query)”. It specifies the displayed relationship between the named quantities or parameters.…
seferim-core · § 6.3 K_norm
This relation defines § 6.3 K_norm in the source section “seferim-core · § 6.3 K_norm”. It specifies the displayed relationship between the named quantities or parameters. Its…
seferim-core · § 6.5 coherence between two θ vectors
This relation defines § 6.5 coherence between two θ vectors in the source section “seferim-core · § 6.5 coherence between two θ vectors”. It specifies the displayed relationship…
seferim-core · § 8.1 F_in
This relation defines § 8.1 F_in in the source section “seferim-core · § 8.1 F_in”. It specifies the displayed relationship between the named quantities or parameters. Its…
seferim-core · § 10.1 Registry[k][i][j]
This relation defines § 10.1 Registry[k][i][j] in the source section “seferim-core · § 10.1 Registry[k][i][j]”. Evaluates oscillatory sine or cosine terms using the stated phase…
seferim-core · § 10.6 Hebbian on strand 0 (representative); ΔW
This relation defines § 10.6 Hebbian on strand 0 (representative); ΔW in the source section “seferim-core · § 10.6 Hebbian on strand 0 (representative); ΔW”. It specifies the…
seferim-core · § 11.1 / § 11.2 dS_i/dt
This relation defines § 11.1 / § 11.2 dS_i/dt in the source section “seferim-core · § 11.1 / § 11.2 dS_i/dt”. It specifies the displayed relationship between the named…
run · § 9 ConsciousnessEngine (174 + 200
This relation defines § 9 ConsciousnessEngine (174 + 200 in the source section “run · § 9 ConsciousnessEngine (174 + 200”. It specifies the displayed relationship between the…