👨‍🎓 Tutorials

Puncc offers hands-on notebooks to help you go from “hello conformal prediction” to more advanced workflows (NLP, object detection, and time series). Pick a tutorial below and run it either on GitHub or in Google Colab.

Tutorial	Description	Link
Introduction Tutorial	Get started with the basics of puncc.	Github or colab
API Tutorial	Learn about puncc’s API.	Github or colab
Tutorial on CP with PyTorch	Learn how to use puncc with PyTorch.	Github or colab
Tutorial on CP with TensorFlow	Learn how to use puncc with TensorFlow / Keras.	Github or colab
Tutorial on Adaptive Conformal Regression	Learn how conformalize regression models to obtain adaptive prediction intervals using methods such as LACP, LWCP and CQR.	Github or colab
Conformal Object Detection	Learn to conformalize an object detector.	Github or colab
Conformal Text Classification	Learn to conformalize a pretrained NLP model.	Github or colab
Conformal Classwise Classification	Learn to use classwise CP for class-conditional coverage.	Github or colab
Custom Conformal Workflow	Build new conformal predictors with custom nonconformity scores, prediction sets and conformalization logic.	Github or colab
Conformal Time Series Forecasting	Learn to conformalize time series models.	Github or colab
Architecture Overview	Detailed overview of puncc’s architecture.	Github or colab

How to use these notebooks

• Run on Colab if you want a zero-install experience (recommended for a quick start).

• Run locally if you want full control over your environment and dependency versions.