andrescorrada/IntroductionToAlgebraicEvaluation

A collection of essays and code on algebraic methods to evaluate noisy judges on unlabeled test data.

36
/ 100
Emerging

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.

No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 9 / 25
Community 10 / 25

How are scores calculated?

Stars

37

Forks

4

Language

Jupyter Notebook

License

CC0-1.0

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.