#uncertainty-quantification
GitHub repositories that have self-applied the topic "uncertainty-quantification" — a creator-tagged metadata that surfaces how AI projects describe themselves.
REPOS Repos for #uncertainty-quantification (top 3 by stars)
Trustworthy AI for satellite conjunction triage using calibrated ML, Bayesian logistic regression, and uncertainty-aware escalation on public CDM data.
Hert4/LLM-Certainty-ConsistencyBackend-agnostic black-box hallucination & RAG-faithfulness detection for LLMs — Probabilistic Certainty & Consistency (arXiv:2601.02574). Works on MLX / OpenAI / vLLM via token logprobs; no model internals, no training.
leo-im/entropy-lensToken-level entropy trajectories from LLM logprobs. Models can measure their own uncertainty — grounding it in truth requires external verification.
RELATED Other topics · full topics ranking →
#claude-code
1,576#ai-agents
1,183#llm
1,086#claude
949#python
829#ai
746#mcp
741#developer-tools
739#codex
525Aggregated by case-insensitive match against topics_json of each repo's latest content snapshot. methodology