Model Confidence Calibration ML Frameworks
Tools and techniques for calibrating neural network confidence scores and probability predictions, including post-hoc methods, metrics, and frameworks. Does NOT include general uncertainty quantification, Bayesian methods, or confidence intervals unrelated to classifier calibration.
There are 21 model confidence calibration frameworks tracked. 2 score above 50 (established tier). The highest-rated is facebookincubator/MCGrad at 57/100 with 18 stars and 215 monthly downloads.
Get all 21 projects as JSON
curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=ml-frameworks&subcategory=model-confidence-calibration&limit=20"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
| # | Framework | Score | Tier |
|---|---|---|---|
| 1 |
facebookincubator/MCGrad
MCGrad is a scalable and easy-to-use tool for multicalibration. It ensures... |
|
Established |
| 2 |
dholzmueller/probmetrics
Post-hoc calibration methods and metrics for classification |
|
Established |
| 3 |
gpleiss/temperature_scaling
A simple way to calibrate your neural network. |
|
Emerging |
| 4 |
yfzhang114/Generalization-Causality
关于domain generalization,domain... |
|
Emerging |
| 5 |
DiTEC-project/DiTEC_WDN_dataset
This repository contains parameter generation, simulation, and encapsulation... |
|
Emerging |
| 6 |
hollance/reliability-diagrams
Reliability diagrams visualize whether a classifier model needs calibration |
|
Emerging |
| 7 |
Affirm/splinator
Splinator: probabilistic calibration with regression splines |
|
Emerging |
| 8 |
VIDA-NYU/pycalibrate
pycalibrate is a Python library to visually analyze model calibration in... |
|
Emerging |
| 9 |
uncbiag/LTS
Local Temperature Scaling for Probability Calibration |
|
Emerging |
| 10 |
lorenzofamiglini/CalFram
Calibration Framework for Machine Learning and Deep Learning |
|
Emerging |
| 11 |
by-liu/MbLS
Code of our method MbLS (Margin-based Label Smoothing) for network... |
|
Emerging |
| 12 |
mdca-loss/MDCA-Calibration
[CVPR 2022] Official code for the paper: "A Stitch in Time Saves Nine: A... |
|
Experimental |
| 13 |
divelab/LECI
The implementation of "Joint Learning of Label and Environment Causal... |
|
Experimental |
| 14 |
kirill-vish/Beyond-INet
Code for experiments for "ConvNet vs Transformer, Supervised vs CLIP: Beyond... |
|
Experimental |
| 15 |
WenjianHuang93/h-Calibration
h-calibration: post-hoc calibration for deep learning classifier |
|
Experimental |
| 16 |
maheeppurohit/epistemic-weight-engine
Epistemic Weight Engine (EWE) — A pre-update gating mechanism for... |
|
Experimental |
| 17 |
jhuang265/Calibrating-LLMs-with-Label-Smoothing
Code to our ICML 2025 Paper "Calibrated Language Models and How to Find Them... |
|
Experimental |
| 18 |
aai-institute/kyle
A library for calibrating classifiers and computing calibration metrics |
|
Experimental |
| 19 |
jsbaan/calibration-on-disagreement-data
Code accompanying the EMNLP 2022 paper "Stop Measuring Calibration When... |
|
Experimental |
| 20 |
MohammadErfan-Jabbari/CNN-Calibration
Investigating calibration in CNNs: Temperature scaling for reliable... |
|
Experimental |
| 21 |
martinferianc/noise
Investigation of how noise perturbations impact neural network calibration... |
|
Experimental |