#confidence-calibration

GitHub repositories that have self-applied the topic "confidence-calibration" — a creator-tagged metadata that surfaces how AI projects describe themselves.

tagged repos

top 1 stars

with tool sigs

shown

REPOS Repos for #confidence-calibration (top 1 by stars)

bhaskargurram-ai/verifydoc

Trust layer for document→JSON extraction & AI agents: calibrated per-field confidence + source grounding + accept/review abstention on any OCR/VLM. Ships VerifyDocBench, a novel grounding-conditioned conformal method, and an MCP server.

Python ★ 1 AI 70 Solo 1 sig live ↗

#confidence-calibration

REPOS Repos for #confidence-calibration (top 1 by stars)

RELATED Other topics · full topics ranking →

#claude-code

#ai-agents

#llm

#claude

#python

#ai

#developer-tools

#mcp

#codex