andrescorrada/IntroductionToAlgebraicEvaluation
A collection of essays and code on algebraic methods to evaluate noisy judges on unlabeled test data.
Frames evaluation as an inverse problem using algebraic postulates derived solely from agreement/disagreement patterns—avoiding probabilistic hyperparameters and out-of-distribution assumptions. The approach is universally applicable across any ensemble of noisy decision-makers (human or machine) through the NTQR framework (number of classifiers, tests, questions, response options), treating it as a black-box evaluation logic that requires no knowledge of agent internals or domain specifics. Includes Python implementations for binary classification cases, positioning algebraic evaluation as a safety mechanism for monitoring AI systems without requiring progressively smarter evaluators.
Stars
37
Forks
4
Language
Jupyter Notebook
License
CC0-1.0
Category
Last pushed
Feb 25, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/andrescorrada/IntroductionToAlgebraicEvaluation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
SENATOROVAI/Normal-equation-solver-multiple-linear-regression-course
Multiple Linear Regression (MLR) models the linear relationship between a continuous dependent...
SENATOROVAI/Normal-equations-scalar-form-solver-simple-linear-regression-course
The normal equations for simple linear regression are a system of two linear equations used to...
SENATOROVAI/underfitting-overfitting-polynomial-regression-course
Underfitting and overfitting are critical concepts in machine learning, particularly when using...
stabgan/Multiple-Linear-Regression
Implementation of Multiple Linear Regression both in Python and R
MathWorks-Teaching-Resources/Machine-Learning-for-Regression
Interactive courseware module that introduces typical workflow, setup, and considerations...