117 lines
2.4 KiB
Markdown
117 lines
2.4 KiB
Markdown
|
||
# Didactopus FAQ
|
||
|
||
## What problem does Didactopus solve?
|
||
|
||
Most learning systems record only test scores or completion status.
|
||
Didactopus records the **structure of knowledge and the trajectory of learning**, allowing deeper analysis of how understanding develops.
|
||
|
||
---
|
||
|
||
## Is Didactopus only for AI learners?
|
||
|
||
No.
|
||
|
||
It is designed for:
|
||
|
||
- human learners
|
||
- AI learners
|
||
- mixed human‑AI learning systems
|
||
|
||
The architecture intentionally treats both types of learners similarly so their progress can be compared and analyzed.
|
||
|
||
---
|
||
|
||
## Why represent knowledge as graphs?
|
||
|
||
Knowledge graphs make relationships explicit:
|
||
|
||
- prerequisites
|
||
- conceptual similarity
|
||
- cross‑domain analogies
|
||
|
||
Graph representations make it easier to visualize and analyze the structure of understanding.
|
||
|
||
---
|
||
|
||
## What is synthesis?
|
||
|
||
Synthesis is the process of **connecting ideas across different domains**.
|
||
|
||
Many major intellectual advances come from recognizing structural similarities between fields.
|
||
|
||
Didactopus supports synthesis by:
|
||
|
||
- allowing cross‑pack concept links
|
||
- visualizing conceptual overlap
|
||
- encouraging learners to explore related domains
|
||
|
||
---
|
||
|
||
## Can learners modify domain packs?
|
||
|
||
Learners can propose improvements through knowledge export artifacts.
|
||
|
||
These proposals may then be reviewed by:
|
||
|
||
- mentors
|
||
- domain pack maintainers
|
||
- automated validation systems
|
||
|
||
Accepted improvements can be incorporated into future pack versions.
|
||
|
||
---
|
||
|
||
## What are artifacts?
|
||
|
||
Artifacts are outputs produced by Didactopus that capture aspects of learning.
|
||
|
||
Examples:
|
||
|
||
- concept graph animations
|
||
- mastery snapshots
|
||
- knowledge export bundles
|
||
- research datasets
|
||
|
||
Artifacts allow learning to be inspected, shared, and reused.
|
||
|
||
---
|
||
|
||
## Why have artifact retention policies?
|
||
|
||
Learning systems can produce large numbers of artifacts.
|
||
|
||
Retention policies allow systems to:
|
||
|
||
- automatically remove temporary artifacts
|
||
- preserve historically important outputs
|
||
- archive discoveries or milestones
|
||
|
||
---
|
||
|
||
## Can Didactopus help build curricula?
|
||
|
||
Yes.
|
||
|
||
Knowledge exports and learner artifacts can be used to produce:
|
||
|
||
- textbooks
|
||
- course modules
|
||
- visual learning materials
|
||
- interactive exercises
|
||
|
||
---
|
||
|
||
## How does Didactopus help AI systems?
|
||
|
||
AI agents can use domain packs as structured skill maps.
|
||
|
||
Learner state tracking allows researchers to observe:
|
||
|
||
- reasoning development
|
||
- concept acquisition
|
||
- cross‑domain transfer
|
||
|
||
This makes Didactopus useful for studying AI learning as well as human learning.
|
||
|