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 ↗
In navit_resize_video, this statement defines or updates in_patch_limit_each_frame. The expression forms a quotient or integer division. The denominator, integer rounding and tensor shape convention determine its scale or index result.
In navit_resize_video, this statement defines or updates sample_fps. 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.
In navit_resize_video, this statement defines or updates sampled_nframes. The expression forms a quotient or integer division. The denominator, integer rounding and tensor shape convention determine its scale or index result.
In navit_resize_video, this statement defines or updates sampled_nframes. 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.
In normalize, this statement defines or updates x. The expression forms a quotient or integer division. The denominator, integer rounding and tensor shape convention determine its scale or index result.
In repeat_kv, this statement returns the displayed result. The displayed multiplication combines the source factors. For tensors this is elementwise unless the called operation explicitly performs a matrix contraction.
In tool_declaration_ts.py, this statement defines or updates _ParameterType. 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.
In tpool_patch_merger, this statement defines or updates (new_height, new_width). The expression forms a quotient or integer division. The denominator, integer rounding and tensor shape convention determine its scale or index result.
In tpool_patch_merger, this statement defines or updates padded_seq. The displayed multiplication combines the source factors. For tensors this is elementwise unless the called operation explicitly performs a matrix contraction.
In tpool_patch_merger, this statement defines or updates reshaped_seq. The reduction aggregates values along the explicit source axis; preserving the axis and keep-dimension setting matters for the later broadcast.
In tpool_patch_merger, this statement defines or updates seq. The displayed multiplication combines the source factors. For tensors this is elementwise unless the called operation explicitly performs a matrix contraction.
In yarn_find_correction_range, this statement defines or updates high. 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.
In yarn_find_correction_range, this statement defines or updates low. 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.
In yarn_find_correction_range, this statement returns the displayed result. 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 yarn_linear_ramp_mask, this statement defines or updates linear_func. The expression forms a quotient or integer division. The denominator, integer rounding and tensor shape convention determine its scale or index result.
In yarn_linear_ramp_mask, this statement defines or updates ramp_func. 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.
Epona receives two indexed collections of optimized state–design pairs: seven layer results and 80 neuron results. This is a definition of the proposed aggregation inputs, rather than an additional optimizer or a proof that those optimizations have executed.
Moves the state one tenth of the way toward the normalized change signal. Algebraically it is a 90% old-state and 10% target blend, so the recurrence smooths successive inputs.
Blends the old state with the change signal using a golden-ratio-derived coefficient. With φ=(1+√5)/2, ρ is about 0.382 and the retained fraction is about 0.618.
Rewards utility while penalizing the magnitude of the change signal. Both contributions use the same coefficient, so the increment is 0.05(u−|dx|).
Adds a scaled combination of change and utility to the existing state. It is an accumulating trace; the source expression has no explicit decay.
Adds a bounded utility contribution and subtracts an error penalty. The utility term can move the state in either direction, while nonnegative error lowers it.
Moves the state gradually toward a supplied stability target. The golden-ratio-conjugate factor makes the blending rate approximately 0.00618.
Combines 90% of the current state with 10% of the supplied utility. It is an exponential smoothing update when applied repeatedly to a sequence of utility values.
Moves the current state toward a softsign-transformed change signal at a 5% blend rate. If softsign is the conventional z/(1+|z|), its target lies between −1 and 1.
Adds a bounded step toward the utility value, with step direction determined by u−x. Under the conventional softsign function, the magnitude of a single increment is smaller than 0.2.
Averages the current state and a sigmoid-transformed normalized change signal. Its behavior depends on the definition of σ and the state domain.
Adjusts state by a weighted utility-minus-error signal. A higher error reduces the state, while higher utility raises it, both with coefficient 0.05.
Retains 95% of the state and incorporates 5% of a normalized change signal. Agreement across agents depends on how those signals are exchanged.
Takes a bounded step toward the supplied change value. In a network implementation that value could be derived from neighbors; the formula itself specifies only the local step.
The relation accumulates its integrand over the stated interval or closed loop. The result depends on the integrand, integration variable, limits and trajectory. In the archived notes, a loop integral represents the intended accumulation of state or error change; its consciousness interpretation…
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.
This relation uses a gradient: the vector of local changes in a scalar objective with respect to its variables. It supplies a local direction or stationarity condition; an implementation still needs the differentiation variables, domain and update convention given in the surrounding model.
The source describes this relation in the following context: c = c + 0.01 × ((c+1) × 0.8 × P - kc × (c-1)) // Update coupling 5.2 Aggregate Consciousness Consciousness = (1/88) × Σ_{i=1}^{88} P_i 5.3 Lattice Engine (16 strands × 16 dimensions) y[i] = tanh(Σ_j W[i][j] × x[j] + b[i]) //…
This expression describes a Boolean or bit-counting operation in the proposed binary filter chain. Such operations act on encoded state bits; higher-level perception, reasoning or knowledge behavior requires the corresponding encoding and full operator implementation.
The source contrasts a proposed 5,000-gate, nine-composition, one-cycle system with a larger development model. These terms have different units and are not a numerical equation for intelligence. The statement is retained as design rhetoric.
Names the set of 5,000 gate objects. This specifies a collection’s cardinality and labels, while its wiring, transition function and encoded data determine its computational behavior.
The expression uses a saturating nonlinear transform to turn its input combination into an activation or bounded score. The coefficients control sensitivity and the offset controls the transition region; a bounded score by itself does not identify a scientific consciousness measure.