How GlyphNet Works
Understanding the technology behind semantic verification.
The Verification Pipeline
Text Input → Claim Extraction → Semantic Encoding → Graph Matching → Confidence Scoring → Results1. Claim Extraction
GlyphNet analyzes your text to identify discrete factual claims:
Input: "Paris is the capital of France and has a population of about 2 million."
Extracted Claims:
- "Paris is the capital of France"
- "Paris has a population of about 2 million"Claims are extracted based on:
- Subject-predicate-object structures
- Quantitative assertions
- Temporal statements
- Causal relationships
2. Semantic Encoding
Each claim is converted into a high-dimensional semantic vector using our Large Concept Model:
"Paris is the capital of France"
↓
[0.234, -0.891, 0.456, ..., 0.123] (384 dimensions)This encoding captures:
- Meaning, not just words
- Relationships between entities
- Context and nuance
3. Knowledge Graph Matching
The encoded claim is matched against our structured knowledge graph:
┌─────────┐
│ Paris │
└────┬────┘
│ capital_of
▼
┌─────────┐
│ France │
└─────────┘The graph contains:
- 30,000+ concepts with explicit relations
- 80,000+ verified edges between concepts
- 10 canonical relation types (is_a, has_part, requires, etc.)
4. Confidence Scoring
Each claim receives a confidence score based on:
| Factor | Weight | Description |
|---|---|---|
| Semantic similarity | 40% | How well the claim matches known facts |
| Graph path strength | 30% | Strength of relational connections |
| Source consensus | 20% | Agreement across multiple paths |
| Recency | 10% | Age of supporting evidence |
5. Result Aggregation
Claims are combined into a verification result:
{
"claims": [
{
"text": "Paris is the capital of France",
"verified": true,
"confidence": 0.98
},
{
"text": "Paris has a population of about 2 million",
"verified": true,
"confidence": 0.85
}
],
"summary": {
"total_claims": 2,
"verified": 2,
"avg_confidence": 0.915
}
}Key Concepts
Semantic vs. Syntactic Matching
Traditional fact-checking matches exact text. GlyphNet matches meaning:
These are equivalent to GlyphNet:
- "Paris is France's capital"
- "The capital of France is Paris"
- "France has Paris as its capital city"Confidence Thresholds
| Confidence | Interpretation |
|---|---|
| 0.90 - 1.00 | High confidence - strongly supported |
| 0.70 - 0.89 | Medium confidence - likely accurate |
| 0.50 - 0.69 | Low confidence - uncertain |
| 0.00 - 0.49 | Unverified - no supporting evidence |
The Flagging Decision
A response is flagged when:
- Any claim has confidence below threshold (default: 0.7)
- Claims contradict each other
- Claims contradict known facts with high confidence
What GlyphNet Cannot Verify
Outside Scope
- Opinions: "Python is the best language"
- Predictions: "It will rain tomorrow"
- Personal experiences: "I enjoyed the movie"
- Very recent events: News from the past 24 hours
Knowledge Limitations
- Highly specialized domains may have limited coverage
- Rapidly changing information may be outdated
- Fictional content is not verified
Architecture Overview
┌─────────────────────────────────────────────────────────┐
│ API LAYER │
│ REST endpoints, authentication, rate limiting │
├─────────────────────────────────────────────────────────┤
│ VERIFICATION ENGINE │
│ Claim extraction, semantic matching, scoring │
├─────────────────────────────────────────────────────────┤
│ LARGE CONCEPT MODEL (LCM) │
│ 384-dimensional semantic embeddings │
├─────────────────────────────────────────────────────────┤
│ KNOWLEDGE GRAPH │
│ 30K concepts, 80K relations, typed edges │
└─────────────────────────────────────────────────────────┘Performance Characteristics
| Metric | Typical Value |
|---|---|
| Latency | 50-200ms per request |
| Throughput | 500+ requests/second |
| Accuracy | 94% on benchmark datasets |
| False positive rate | < 3% |