# US 2026/0073149 A1 · Latent Slice Budgeting for Cognitive Manifold Using ADM Formalism

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0073149 A1
- Document ID: US20260073149A1
- Status: Published application
- Kind: A1
- Application number: 19/390,475
- Filed: 2025-11-14
- Published: 2026-03-12
- Earliest claimed: 2024-05-23
- Assignees: Atombeam Technologies Inc.
- Applicants: AtomBeam Technologies Inc.
- Inventors: Brian Galvin; Alexandria Tucker
- Web page: https://patentgrep.com/patent/US20260073149A1

## CPC

- G06F 40/30: Semantic analysis
- G06F 16/3325: {Reformulation based on results of preceding query}
- G06F 16/3329: Natural language query formulation
- G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
- G06N 3/045: Combinations of networks
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/047: Probabilistic or stochastic networks
- G06N 3/08: Learning methods
- G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections
- G06N 3/088: Non-supervised learning, e.g. competitive learning
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 5/04: Inference or reasoning models
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/00: Machine learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Systems and methods for latent slice budgeting on a persistent cognitive machine (PCM) that uses a continuous, differentiable, cognitive manifold in geometric space to allow a computer to engage in human-like thought processes. The PCM with cognitive manifold represents a fundamental advancement in artificial intelligence beyond current probabilistic AI system such as large language models (LLMs) and similar reasoning models. A PCM with cognitive manifold performs cognition on a thought manifold in a continuous, differentiable, thought manifold in geometric space as opposed to probabilistic prediction in a discontinuous, anisotropic, and topologically fractured vector space. Methods for latent slice budgeting on the cognitive manifold are disclosed that foliation of the cognitive manifold into time slices and budgeting change between the time slices.

## Claims

### Claim 1

A computer system configured to execute software instructions stored on nontransitory machine-readable storage media, wherein the software instructions comprise instructions that:
foliate a differentiable cognitive manifold into time slices;
receive a salience map for the differentiable cognitive manifold;
compute a budget function for the differentiable cognitive manifold from the salience map;
receive a cognition event for processing on the cognitive manifold; and
compute one or more reasoning trajectories across the cognitive manifold from the cognition event as sequence of the time slices, wherein at each time slice the budget function is applied to the computation of the one or more reasoning trajectories to constrain a magnitude of change from one slice to the next.

### Claim 2 (depends on 1)

The computer system of claim 1, wherein:
the salience map comprises regions of high salience and low salience on the differentiable cognitive manifold; and
a plurality of budget functions are computed wherein budget functions for regions of high salience allow for greater variability than budget functions for regions of low salience.

### Claim 3 (depends on 1)

The computer system of claim 1, wherein:
an extrinsic curvature tensor is applied to capture the deformation of geodesics on the cognitive manifold as the cognitive manifold evolves.

### Claim 4 (depends on 1)

The computer system of claim 1, wherein the budget function is dependent on cognitive potentials drawn comprising compression pressure, goal potential, and usage statistics.

### Claim 5 (depends on 1)

The computer system of claim 1, wherein:
the cognitive event comprises data from a plurality of heterogenous data sources, each heterogenous data source providing modality-specific time indications; and
the software instructions further comprise instructions that provide temporal reconciliation of the data by mapping the modality-specific time indications to a global time index by applying lapse and shift functions to the data.

### Claim 6 (depends on 1)

The computer system of claim 1, wherein the foliation of the cognitive manifold is performed according to the following equations:
M
=
⋃
t
≥
0
M
t
,
M
t
=
(
M
,
g
t
)
wherein:
Mt denotes the slice of the manifold at PCM time t, endowed with metric tensor gt;
each slice encodes the semantic geometry of cognition at that time step;
a transition Mt→Mt+1 represents the evolution of cognition under new information, compression, and internal processing; and
evolution of the metric is expressed as gt+1=gt+Δgt.

### Claim 7 (depends on 6)

The computer system of claim 6, wherein
the salience map comprises regions of high salience and low salience on the differentiable cognitive manifold;
a plurality of budget functions are computed wherein budget functions for regions of high salience allow for greater variability than budget functions for regions of low salience; and
for each point p∈Mt, the budget function takes the form ∥Δg_t(p)∥≤ε(p), wherein ε(p) is determined by the semantic role of p.

### Claim 8 (depends on 7)

The computer system of claim 7, wherein:
an extrinsic curvature tensor is applied to capture the deformation of geodesics on the cognitive manifold as the cognitive manifold evolves; and
the extrinsic curvature tensor is the form of ∥Kt(p)∥≤κ(p), where κ(p) is chosen to be smaller in high-salience areas to prevent unstable distortion of reasoning paths and higher in low-salience areas to allow for greater explorative reasoning.

### Claim 9 (depends on 8)

The computer system of claim 8, wherein the budget function is made dependent on cognitive potentials through the equation:
ϵ
⁡
(
p
)
=
f
⁡
(
P
⁡
(
p
)
,
φ
⁡
(
p
)
,
U
⁡
(
p
)
)
,
where P(p) denotes compression pressure at p, φ(p) denotes goal potential, and U(p) encodes usage statistics of the region.

### Claim 10 (depends on 9)

The computer system of claim 9, wherein:
the cognitive event comprises data from a plurality of heterogenous data sources, each heterogenous data source providing modality-specific time indications;
the software instructions further comprise instructions that provide temporal reconciliation of the data by mapping the modality-specific time parameters τedge to a global time index according to
t
=
R
edge
(
τ
edge
;
L
,
S
)
,
where L is a lapse function implementing rescaling of a local modality clock, and S is a shift function introducing offsets necessary to align the modality-specific time parameters across the heterogenous data sources.

### Claim 11

A method comprising using a computer system to perform the steps of:
foliating a differentiable cognitive manifold into time slices;
receive a salience map for the differentiable cognitive manifold;
computing a budget function for the differentiable cognitive manifold from the salience map;
receiving a cognition event for processing on the cognitive manifold; and
computing one or more reasoning trajectories across the cognitive manifold from the cognition event as sequence of the time slices, wherein at each time slice the budget function is applied to the computation of the one or more reasoning trajectories to constrain a magnitude of change from one slice to the next.

### Claim 12 (depends on 11)

The method of claim 11, wherein:
the salience map comprises regions of high salience and low salience on the differentiable cognitive manifold; and
the method further comprises the step of computing a plurality of budget functions budget functions for regions of high salience allow for greater variability than budget functions for regions of low salience.

### Claim 13 (depends on 11)

The method of claim 11, comprising the further step of:
applying an extrinsic curvature tensor to capture the deformation of geodesics on the cognitive manifold as the cognitive manifold evolves.

### Claim 14 (depends on 11)

The method of claim 11, wherein the budget function is dependent on cognitive potentials drawn comprising compression pressure, goal potential, and usage statistics.

### Claim 15 (depends on 11)

The method of claim 11, wherein:
the cognitive event comprises data from a plurality of heterogenous data sources, each heterogenous data source providing modality-specific time indications; and
the method further comprises the step of providing temporal reconciliation of the data by mapping the modality-specific time indications to a global time index by applying lapse and shift functions to the data.

### Claim 16 (depends on 11)

The method of claim 11, wherein the foliation of the cognitive manifold is performed according to the following equations:
M
=
⋃
t
≥
0
M
t
,
M
t
=
(
M
,
g
t
)
wherein:
Mt denotes the slice of the manifold at PCM time t, endowed with metric tensor gt;
each slice encodes the semantic geometry of cognition at that time step;
a transition Mt→Mt+1 represents the evolution of cognition under new information, compression, and internal processing; and
evolution of the metric is expressed as gt+1=gt+Δgt.

### Claim 17 (depends on 16)

The method of claim 16, wherein
the salience map comprises regions of high salience and low salience on the differentiable cognitive manifold;
the method further comprises the step of computing a plurality of budget functions budget functions for regions of high salience allow for greater variability than budget functions for regions of low salience; and
for each point p∈Mt, the budget function takes the form ∥Δg_t(p)∥≤ε(p), wherein ε(p) is determined by the semantic role of p.

### Claim 18 (depends on 17)

The method of claim 17, wherein:
the method further comprises the step of applying an extrinsic curvature tensor to capture the deformation of geodesics on the cognitive manifold as the cognitive manifold evolves; and
the extrinsic curvature tensor is the form of ∥Kt(p)∥≤κ(p), where κ(p) is chosen to be smaller in high-salience areas to prevent unstable distortion of reasoning paths and higher in low-salience areas to allow for greater explorative reasoning.

### Claim 19 (depends on 18)

The method of claim 18, wherein the budget function is made dependent on cognitive potentials through the equation:
ϵ
⁡
(
p
)
=
f
⁡
(
P
⁡
(
p
)
,
φ
⁡
(
p
)
,
U
⁡
(
p
)
)
,
where P(p) denotes compression pressure at p, φ(p) denotes goal potential, and U(p) encodes usage statistics of the region.

### Claim 20 (depends on 19)

The method of claim 19, wherein:
the cognitive event comprises data from a plurality of heterogenous data sources, each heterogenous data source providing modality-specific time indications;
the method further comprises the step of providing temporal reconciliation of the data by mapping the modality-specific time parameters τedge to a global time index according to
t
=
R
edge
(
τ
edge
;
L
,
S
)
,
where L is a lapse function implementing rescaling of a local modality clock, and S is a shift function introducing offsets necessary to align the modality-specific time parameters across the heterogenous data sources.
