THE CONSCIOUSNESS ATLAS
Read. Experiment. Follow the evidence.
Every recovered mathematical record has an individual page. Browse original equations, code expressions, indexed components, parameter definitions, and explicitly unresolved source slots.
Counts refer to mathematical records, including implemented expressions and generated instances. They are not counts of independently validated theories. Exact occurrences and unresolved slots remain traceable. Read the complete 1–516 source index ↗ · Inspect the scan decisions ↗
The chosen state or action is intended to minimize surprise plus uncertainty minus value. Increasing the value term can lower the objective, while larger surprise or uncertainty raises it. The minimization variable and candidate domain are omitted in the printed expression.
Select a candidate program that minimizes residual bug loss plus a weighted cost of changing the original program. The displayed compile, type, test and safety predicates restrict which candidates are eligible. The objective balances two costs; it does not by itself prove that the globally smallest…
Apply the repair operator R to the current program and current diagnostics to obtain the next program. Repeating this interface describes an iterative repair process; it does not specify how candidates are generated or when the loop stops.
Map a nonnegative gradient magnitude r to r/(1+r). It is zero at r=0, increases monotonically, and approaches one for large r, limiting the influence of very large gradients.
Combine state change, produced artifacts, information gain and goal progress with four weights. The terms indicate what counts as progress, but neither the image nor this formula defines how the features are measured.
The equality assigns a descriptive name to H^16. It identifies an intended sixteen-domain recursive family organization; it is not a numerical identity or a measurement of AGI.
Convert action values into a distribution over actions by applying softmax across the available action set. Actions with larger values receive larger probability, while finite values keep every available action at positive probability.
The state velocity is decomposed into four operators: diffusion D spreads activation, nonlinear emergence N describes interactions, external force F represents inputs or pressure, and transport T moves information or state. This is a general dynamical-system template. Concrete functions and an…
Assign a score of one at z=1 and decrease it as the absolute distance from one increases. For finite real z the score lies in (0,1]. It is a simple proximity function rather than a causal integrated-information calculation.
The notes combine the named components with tensor-product or direct-sum-style notation. The expression records the proposed organization of the model. Concrete dimensions, operator definitions and evaluation order are required before the composition is an executable numerical rule.
The expression assigns a hash-derived representation to the listed state components. A hash is a many-to-one identifier unless a reversible representation is explicitly specified; the notation alone does not establish reconstruction of the original state.
The source describes this relation in the following context: A 5000-bit deterministic logic circuit providing computational substrate: 9.1 Phase Updates phase_DNA(t+1) = (phase_DNA(t) + 0.013618) mod 1 // [Eq. 80] phase_Fib(t+1) = (phase_Fib(t) + 1/φ) mod 1 // [Eq. 81] 9.2 Combined…
Packages DNA structure, gates, loop score, coherence driver, binary representation, seven layer losses, device loss and state/design/environment objects into one model tuple. A tuple collects these definitions; it does not itself supply an algorithm that evaluates them.
Names the probability of one gate-state transition conditional on the DNA structure. This shorthand needs a normalized transition distribution to define a usable stochastic model.
Defines a set of component pairs satisfying f(d_i,d_j)=0. The set-builder notation expresses a compatibility constraint; the source does not provide a complete definition of f or the domains of the components in this shorthand.
Defines K as a conditional probability of the next gate state given the current gate state and DNA structure. A valid kernel needs nonnegative probabilities normalized over every possible next state.
This is basis component 0 of the documented 16-dimensional memory representation. It evaluates a sine and a cosine at the same golden-ratio-scaled frequency and adds them. The value is a deterministic feature of the input coordinate x. A fixed set of 16 such values does not uniquely encode every…
This is basis component 1 of the documented 16-dimensional memory representation. It evaluates a sine and a cosine at the same golden-ratio-scaled frequency and adds them. The value is a deterministic feature of the input coordinate x. A fixed set of 16 such values does not uniquely encode every…
This is basis component 10 of the documented 16-dimensional memory representation. It evaluates a sine and a cosine at the same golden-ratio-scaled frequency and adds them. The value is a deterministic feature of the input coordinate x. A fixed set of 16 such values does not uniquely encode every…
This is basis component 11 of the documented 16-dimensional memory representation. It evaluates a sine and a cosine at the same golden-ratio-scaled frequency and adds them. The value is a deterministic feature of the input coordinate x. A fixed set of 16 such values does not uniquely encode every…
This is basis component 12 of the documented 16-dimensional memory representation. It evaluates a sine and a cosine at the same golden-ratio-scaled frequency and adds them. The value is a deterministic feature of the input coordinate x. A fixed set of 16 such values does not uniquely encode every…
This is basis component 13 of the documented 16-dimensional memory representation. It evaluates a sine and a cosine at the same golden-ratio-scaled frequency and adds them. The value is a deterministic feature of the input coordinate x. A fixed set of 16 such values does not uniquely encode every…
This is basis component 14 of the documented 16-dimensional memory representation. It evaluates a sine and a cosine at the same golden-ratio-scaled frequency and adds them. The value is a deterministic feature of the input coordinate x. A fixed set of 16 such values does not uniquely encode every…
This is basis component 15 of the documented 16-dimensional memory representation. It evaluates a sine and a cosine at the same golden-ratio-scaled frequency and adds them. The value is a deterministic feature of the input coordinate x. A fixed set of 16 such values does not uniquely encode every…
This is basis component 2 of the documented 16-dimensional memory representation. It evaluates a sine and a cosine at the same golden-ratio-scaled frequency and adds them. The value is a deterministic feature of the input coordinate x. A fixed set of 16 such values does not uniquely encode every…
This is basis component 3 of the documented 16-dimensional memory representation. It evaluates a sine and a cosine at the same golden-ratio-scaled frequency and adds them. The value is a deterministic feature of the input coordinate x. A fixed set of 16 such values does not uniquely encode every…
This is basis component 4 of the documented 16-dimensional memory representation. It evaluates a sine and a cosine at the same golden-ratio-scaled frequency and adds them. The value is a deterministic feature of the input coordinate x. A fixed set of 16 such values does not uniquely encode every…
This is basis component 5 of the documented 16-dimensional memory representation. It evaluates a sine and a cosine at the same golden-ratio-scaled frequency and adds them. The value is a deterministic feature of the input coordinate x. A fixed set of 16 such values does not uniquely encode every…
This is basis component 6 of the documented 16-dimensional memory representation. It evaluates a sine and a cosine at the same golden-ratio-scaled frequency and adds them. The value is a deterministic feature of the input coordinate x. A fixed set of 16 such values does not uniquely encode every…
This is basis component 7 of the documented 16-dimensional memory representation. It evaluates a sine and a cosine at the same golden-ratio-scaled frequency and adds them. The value is a deterministic feature of the input coordinate x. A fixed set of 16 such values does not uniquely encode every…
This is basis component 8 of the documented 16-dimensional memory representation. It evaluates a sine and a cosine at the same golden-ratio-scaled frequency and adds them. The value is a deterministic feature of the input coordinate x. A fixed set of 16 such values does not uniquely encode every…
This is basis component 9 of the documented 16-dimensional memory representation. It evaluates a sine and a cosine at the same golden-ratio-scaled frequency and adds them. The value is a deterministic feature of the input coordinate x. A fixed set of 16 such values does not uniquely encode every…
The expression assigns a hash-derived representation to the listed state components. A hash is a many-to-one identifier unless a reversible representation is explicitly specified; the notation alone does not establish reconstruction of the original state.
The source describes this relation in the following context: 9.1 Phase Updates phase_DNA(t+1) = (phase_DNA(t) + 0.013618) mod 1 // [Eq. 80] phase_Fib(t+1) = (phase_Fib(t) + 1/φ) mod 1 // [Eq. 81] 9.2 Combined Bias bias = fract(phase_DNA + phase_Fib) - 0.5 // [Eq. 82] flip =…
In DeepseekV3Attention.__init__, this statement defines or updates self.kv_a_proj_with_mqa. The addition or subtraction updates the named state or combines residual contributions. The input shapes and the order in the surrounding forward path must be preserved.
In DeepseekV3Attention.__init__, this statement defines or updates self.kv_b_proj. The displayed multiplication combines the source factors. For tensors this is elementwise unless the called operation explicitly performs a matrix contraction.
In DeepseekV3Attention.__init__, this statement defines or updates self.o_proj. The displayed multiplication combines the source factors. For tensors this is elementwise unless the called operation explicitly performs a matrix contraction.
In DeepseekV3Attention.__init__, this statement defines or updates self.q_b_proj. The displayed multiplication combines the source factors. For tensors this is elementwise unless the called operation explicitly performs a matrix contraction.
In DeepseekV3Attention.__init__, this statement defines or updates self.q_head_dim. The addition or subtraction updates the named state or combines residual contributions. The input shapes and the order in the surrounding forward path must be preserved.
In DeepseekV3Attention.__init__, this statement defines or updates self.q_proj. The displayed multiplication combines the source factors. For tensors this is elementwise unless the called operation explicitly performs a matrix contraction.
In DeepseekV3Attention.forward, this statement defines or updates attn_output. The matrix or indexed contraction combines the stated axes. Compatible tensor dimensions and the transposes in this exact source expression determine the output.
In DeepseekV3Attention.forward, this statement defines or updates attn_output. The displayed multiplication combines the source factors. For tensors this is elementwise unless the called operation explicitly performs a matrix contraction.
In DeepseekV3Attention.forward, this statement defines or updates attn_output. This statement evaluates the named projection, normalization or numeric transform with the source arguments. Its learned parameters and exact input shape are defined by the surrounding module.