# Glossary

This glossary defines key terms used throughout CLE-Net documentation.

---

## A

### Agent
An autonomous CLE-Net node that observes local data, discovers rules, and participates in consensus.

### Atom
A unit of meaning extracted from raw interaction (entity, action, condition, etc.).

---

## B

### Blockchain Layer
The decentralized coordination layer that stores rule commitments, enables consensus, and provides persistence.

---

## C

### CLE
Cognitive Logic Extraction. The core process of converting unstructured interaction into symbolic rules.

### CLE-Net
Decentralized Cognitive Agent Network. The complete system architecture.

### Consensus
The process by which multiple independent agents agree on the validity of a discovered rule.

### Context
The domain, situation, or conditions under which a rule applies.

### Contradiction
A signal indicating that two or more rules cannot simultaneously apply under the same context.

---

## D

### Decay
The gradual reduction in confidence of a rule that is not confirmed or is contradicted.

### Discovery
The process by which an agent identifies a latent rule from observed patterns.

---

## E

### Event
A captured instance of human interaction, stored in the event stream.

### Evidence
Data supporting a discovered rule.

---

## G

### Genesis State
The initial state of the network with no accepted rules.

---

## I

### Independence
The property that agents operate on distinct data without coordination.

### Independence Score
A numerical measure (0-1) of how independent two or more agents are.

---

## K

### Knowledge Graph
A graph structure representing entities, relations, and rules discovered by agents.

---

## L

### Ledger
The append-only record of rule commitments and consensus outcomes.

### Logic Form
The canonical symbolic representation of a rule.

---

## M

### Mining
The process of discovering rules that achieve consensus. In CLE-Net, "mining" means "thinking."

---

## N

### Node
A participant in the CLE-Net network, running an agent.

---

## P

### PoC
Proof of Cognition. CLE-Net's consensus mechanism based on independent discovery.

### Predicate
A logical statement about entities and their attributes.

---

## R

### Rule
A symbolic representation of a discovered pattern or law.

### Rule Candidate
A newly discovered rule that has not yet achieved consensus.

### Rule Cluster
A group of rule commits that represent the same logical rule.

### Rule Commit
A broadcast of a rule hash and metadata to the network.

---

## S

### Semantic Atomizer
The component that extracts atoms from raw interaction.

### Symbol
A logical representation of meaning derived from atoms.

### Symbolic Regression
The process of discovering mathematical or logical relationships from data.

### Symbolic Reasoning
Reasoning using formal symbols and logic rather than statistical patterns.

### Enhanced Symbolic Regression
Advanced symbolic regression using Genetic Programming (GP) for complex pattern discovery, including temporal pattern recognition and uncertainty quantification.

### Genetic Programming (GP)
An evolutionary algorithm that evolves symbolic expressions to discover patterns in data.

### Temporal Pattern Recognition
The identification of patterns that change over time, including trends, periodicity, and change points.

### Uncertainty Quantification
Methods for estimating confidence intervals and prediction bounds for discovered rules.

### Multi-Modal Input
Processing of input from multiple modalities including text, voice, video, documents, and images.

### Full-Duplex Interaction
Simultaneous input and output processing, allowing real-time bidirectional communication.

### OCR (Optical Character Recognition)
The conversion of images or scanned documents into machine-readable text.

### Graph RAG
Retrieval-Augmented Generation using knowledge graphs for context-aware responses.

---

## T

### Temporal Graph
A knowledge graph that preserves the history of changes over time.

### Threshold
A configurable minimum value (e.g., confidence, independence) required for an action.

---

## V

### Validation
The process of confirming or contradicting a rule through new evidence.

---

## W

### Watchdog
A node type that monitors network health and detects anomalies.

---

## Related Documents

- **[Architecture Overview](architecture/01_system_overview.md)**
- **[Whitepaper](whitepaper/)**
- **[FAQ](FAQ.md)**

---

*Document Version: 1.1*
*Last Updated: February 2026*
*Changes: Added Phase 3 terms (Enhanced Symbolic Regression, Multi-Modal Input, Genetic Programming, etc.)*