Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update readme #36

Merged
merged 1 commit into from
Nov 8, 2024
Merged

Update readme #36

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
49 changes: 49 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,6 +136,55 @@ sequenceDiagram

This implementation enables the system to quickly adapt to new narrative contexts with minimal data, making it particularly valuable for modeling emerging story dynamics.

### nfs_bias_research.py

This PoC explores bias detection and evolution in narrative fields through story-based analysis. Key features include:

- Natural story evolution simulation without mechanical state tracking
- Bias pattern detection through narrative field dynamics
- Interactive story generation with LLM integration
- Analysis of character perspective resonances
- Narrative tension and resolution tracking

### bayes_updating.py

This PoC implements Bayesian belief updating for analyzing evolving narratives. Key features include:

- Real-time belief state tracking and visualization
- Evidence-based belief updating
- Confidence level monitoring
- Shift magnitude interpretation
- Comprehensive belief evolution analysis

### poc_story_vs_narrative.py

This PoC investigates the relationship between individual stories and broader narratives. Key features include:

- Story modification through various narrative lenses
- Similarity scoring between original and modified stories
- Category-based story analysis
- Efficient embedding caching
- Detailed modification tracking and logging

## Latest Experimental Results

The recent experiments demonstrate several key findings:

1. **Bias Evolution**: The bias research implementation shows how narratives naturally evolve through field interactions, revealing emergent patterns in perspective shifts.

2. **Belief Dynamics**: The Bayesian updating system effectively tracks belief evolution with:
- Rapid adaptation to new evidence
- Granular confidence tracking
- Clear visualization of belief shifts
- Interpretable magnitude classifications

3. **Story-Narrative Relationship**: The story vs narrative experiments reveal:
- Quantifiable relationships between individual stories and broader narratives
- Measurable impact of narrative modifications
- Consistent patterns in story evolution
Comment on lines +182 to +184
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nitpick (documentation): Add periods at the end of bullet points for consistency

Other bullet points in the document end with periods. Consider adding periods here for consistency.


These findings contribute to our understanding of narrative field dynamics and provide new tools for analyzing complex social systems.

## Development Guidelines

- Follow PEP 8 style guide and use Black for code formatting.
Expand Down
Loading