Stop guessing confidence thresholds: calibrate, threshold, and drift-check typed decision models (TypeSafe Jev) against an LLM teacher.
-
Updated
Sep 18, 2026 - Python
#
confidence-thresholds
Here are 3 public repositories matching this topic...
Runnable samples for Jev, TypeSafe AI's System One model. Send state and questions carrying their own answer options, then branch on the typed value that comes back.
python code-samples text-classification examples decision-making calibration classification typesafe uv structured-output systemone llm structured-generation jev typesafe-ai system-one confidence-thresholds
-
Updated
Oct 7, 2026
A modular, reproducible pipeline that tests whether biological images can be grouped by species without training labels. It extracts features using foundation models, runs multiple unsupervised clustering methods, and evaluates clustering quality using ground-truth species labels. It also helps to annotate the clusters using BioCLIP-2
application classification uncertainty-quantification human-in-the-loop foundation-models species-annotation dinov3 bioclip2 confidence-thresholds species-clustering
-
Updated
Nov 9, 2026 - Python
Add this topic to your repo
To associate your repository with the confidence-thresholds topic, visit your repo's landing page and select "manage topics."