Ziechoes/reasoning-invariance-benchmark

Experiments testing whether LLM reasoning trajectories remain invariant when constraint layers are applied. If reasoning paths diverge under identical logical problems, this suggests architectural coupling between inference state and constraint enforcement.

12
/ 100
Experimental
No License No Package No Dependents
Maintenance 10 / 25
Adoption 1 / 25
Maturity 1 / 25
Community 0 / 25

How are scores calculated?

Stars

1

Forks

Language

Python

License

Last pushed

Mar 04, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/Ziechoes/reasoning-invariance-benchmark"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.