# nayakbhupen/Spnda

> A library for epistemic uncertainty quantification and LLM hallucination detection via Exact-Match Normalized Entropy (R_sc), requiring no NLI models or GPU and running ~90,000x faster than Semantic Entropy.

- Magnitude: 0.0 out of 10 — Quiet
- Stars: 32 total · +0 stars on 2026-09-23 (UTC), ≈ 0 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · Created: 2026-09-01 · Last push: 2026-09-17
- GitHub: https://github.com/nayakbhupen/Spnda · Homepage: https://doi.org/10.5281/zenodo.22233648 · Page: https://gitnova.dev/en/r/nayakbhupen/Spnda

## Useful for

- Wrap an OpenAI-compatible client with spanda.wrap to block uncertain answers before they reach users
- Run spnda serve as a proxy to Ollama or vLLM and check answers via the X-Spanda-Rsc header
- Run batch_compute_rsc over a list of samples to filter hallucinations in an offline pipeline

## Why it’s here

- The repository is 22 days old and already has 32 stars.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 1
- Issues and pull requests: 0
- Watchers: 0
- Average over the last week: 0 per day
- Usual pace: 2 per day
- Latest release: v0.2.2 (2026-09-07)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 11 days

09-13 0.9, 09-14 0.8, 09-15 0.3, 09-16 0.4, 09-17 0.3, 09-18 0.4, 09-19 0.0, 09-20 0.5, 09-21 0.0, 09-22 0.0, 09-23 0.0

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-23 09:06 UTC, updated every 30 minutes.