Learning Graph Quality Metrics Report

Overview

• Total Concepts: 400
• Foundational Concepts (no prerequisites, other concepts depend on them): 2
• Terminal Nodes (nothing depends on them, but have prerequisites): 140
• Orphaned Nodes (completely disconnected, no edges): 0
• Concepts with Dependencies: 398
• Average Dependencies per Concept: 2.41

Overall Quality Score

94/100 — Excellent

The graph is a single connected DAG with no cycles, self-dependencies, or orphaned concepts. Its 35% terminal-node share is within the healthy range, and 958 edges provide multiple learning pathways. The 26-concept longest path is intentionally deep and should be monitored when chapters are sequenced.

Graph Structure Validation

• Valid DAG Structure: ✅ Yes
• Self-Dependencies: None detected ✅
• Cycles Detected: 0

Foundational Concepts

These concepts have no prerequisites:

• 1: Artificial Intelligence
• 17: Customer Research

Dependency Chain Analysis

• Maximum Dependency Chain Length: 26

Longest Learning Path:

1. Artificial Intelligence (ID: 1)
2. Generative AI (ID: 2)
3. Large Language Models (ID: 3)
4. Model Instructions (ID: 6)
5. Model Responses (ID: 7)
6. Synthetic Users (ID: 9)
7. Synthetic Personas (ID: 10)
8. Customer Persona (ID: 81)
9. Persona Purpose (ID: 82)
10. Persona Template (ID: 83)
11. Constraint Definition (ID: 198)
12. Evaluation Instructions (ID: 199)
13. Output Instructions (ID: 200)
14. Structured Output (ID: 211)
15. Agent Context (ID: 245)
16. Isolated Context (ID: 268)
17. Parallel Evaluation (ID: 269)
18. Response Aggregation (ID: 286)
19. Pattern Detection (ID: 351)
20. Contradiction Detection (ID: 356)
21. Risk Assessment (ID: 361)
22. Recommendation Priority (ID: 365)
23. Recommendation List (ID: 396)
24. Executive Dashboard (ID: 398)
25. Capstone System (ID: 399)
26. Scalable Research Process (ID: 400)

Terminal Nodes Analysis

Terminal nodes are concepts that nothing else depends on but have prerequisites. They represent natural endpoints of learning paths — culminating or specialized concepts.

• Total Terminal Nodes: 140 (35.0% of all concepts)
• Healthy Range: 5-40% of total concepts

Concepts at the end of learning paths:

• 12: Synthetic User Research
• 15: AI Focus Groups
• 16: Brand Stress Testing
• 49: Automation Bias
• 50: Confirmation Bias
• 51: Selection Bias
• 52: Cultural Bias
• 53: Stereotype Risk
• 54: False Confidence
• 57: Human Oversight
• 59: Ethical AI Use
• 71: Uncertainty Disclosure
• 75: Harm Assessment
• 76: Misuse Prevention
• 78: Audit Trail
• 79: Decision Accountability
• 80: Ethical Escalation
• 109: Media Habits
• 110: Channel Preferences
• 111: Technology Comfort

...and 120 more

Orphaned Nodes Analysis

Orphaned nodes are completely disconnected concepts with no inbound AND no outbound edges. These indicate a quality problem — every concept should connect to the graph.

• Total Orphaned Nodes: 0

✅ No orphaned nodes detected. All concepts are connected to the graph.

Connected Components

• Number of Connected Components: 1

✅ All concepts are connected in a single graph.

Indegree Analysis

Top 10 concepts that are prerequisites for the most other concepts:

Rank	Concept ID	Concept Label	Indegree
1	81	Customer Persona	53
2	121	Customer Segmentation	40
3	181	Prompt Engineering	32
4	321	Evaluation Framework	29
5	17	Customer Research	25
6	291	Marketing Asset	25
7	261	Multi-Agent System	24
8	161	Persona Consistency	22
9	241	AI Agent	22
10	18	Market Research	20

Outdegree Distribution

Dependencies	Number of Concepts
0	2
1	16
2	258
3	91
4	19
5	8
6	5
7	1

Recommendations

• ✅ Terminal node percentage (35.0%): Within healthy range (5-40%)
• ✅ DAG structure verified: Graph supports valid learning progressions
• ℹ️ Long dependency chains (26): Ensure students can follow extended learning paths

---

Report generated by learning-graph-reports/analyze_graph.py