Selective Prediction Python Packages

jevrag

A pluggable decision substrate for RAG pipelines; explicit, calibrated state → Decision → confidence → action gates, with Jev as the first swappable backend.

actseal

Test frozen model decision policies with risk/coverage bounds, provider-fault checks and offline replay.

seapig

Uncertainty based selection of compatible inputs

quaesitor-zero

A tiny, offline check for abstention in text-to-SQL and RAG-over-warehouse assistants: does it say it cannot answer instead of returning a confident wrong number? No model access, no network.

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.

masstrust

Calibrated trust and abstention for MS/MS molecular annotations

abstain-bench

How often does your verifier claim success on input it could not check? A benchmark for unearned passes

score-select

Code Repository for SCoRE paper

incerto

A comprehensive library for uncertainty quantification in machine learning.