cff-version: 1.2.0
message: "If you use this working paper, please cite the version you consulted."
title: "Machine Learning G2 Betti Numbers from Orientifold Calabi-Yau Data: A Leakage-Audited Predictive Test"
type: article
authors:
  - family-names: Rajan
    given-names: Mayone Maha
    orcid: https://orcid.org/0009-0006-8135-5306
version: 2.0.0
date-released: 2026-06-10
url: https://research.mahastrategies.com/papers/machine_learning_g2_betti
license: CC-BY-4.0
keywords:
  - working paper
  - Maha Strategies Research
abstract: "Leakage-audited methods study"