{"@context":"https://schema.org","@type":"ScholarlyArticle","identifier":"https://research.mahastrategies.com/papers/machine_learning_g2_betti","name":"Machine Learning G2 Betti Numbers from Orientifold Calabi-Yau Data: A Leakage-Audited Predictive Test","version":"2.0.0","dateModified":"2026-06-10","creativeWorkStatus":"Working paper","reviewStatus":"Not peer reviewed","url":"https://research.mahastrategies.com/papers/machine_learning_g2_betti","encoding":[{"@type":"MediaObject","encodingFormat":"application/pdf","contentUrl":"https://research.mahastrategies.com/papers/machine_learning_g2_betti.pdf"},{"@type":"MediaObject","encodingFormat":"application/x-bibtex","contentUrl":"https://research.mahastrategies.com/papers/machine_learning_g2_betti/citation.bib"},{"@type":"MediaObject","encodingFormat":"text/yaml","contentUrl":"https://research.mahastrategies.com/papers/machine_learning_g2_betti/citation.cff"}],"citation":[{"id":"machine_learning_g2_betti-ref-1","text":"Feature leakage (h¹·¹₊, h¹·²₊ removed from inputs; confirmed against Eqs. 7–8).","verification":"unclassified"},{"id":"machine_learning_g2_betti-ref-2","text":"Data provenance (database confirmed real and public; lineage to Kreuzer-Skarke and the Altman et al. / Gao et al. orientifold databases verified against primary literature).","verification":"unclassified"},{"id":"machine_learning_g2_betti-ref-3","text":"Baseline (OLS fit and reported alongside the DNN; b₃ reversal documented).","verification":"unclassified"},{"id":"machine_learning_g2_betti-ref-4","text":"G₂ holonomy claim (downgraded to explicit assumption; orbifold resolution not claimed as proven).","verification":"unclassified"},{"id":"machine_learning_g2_betti-ref-5","text":"b₃ formula wording (corrected from \"database shows\" to algebraic identity).","verification":"unclassified"},{"id":"machine_learning_g2_betti-ref-6","text":"Confirm the 12,930-entry / 377-family counts against a direct query of the filtered database (a `len()` check on the loaded dataframe).","verification":"unclassified"},{"id":"machine_learning_g2_betti-ref-7","text":"Confirm the DNN b₃ MSE (0.9800) against the raw output file for internal consistency with R² = 0.9983.","verification":"unclassified"},{"id":"machine_learning_g2_betti-ref-8","text":"Repository URL (§6).","verification":"unclassified"},{"id":"machine_learning_g2_betti-ref-9","text":"Final human read of the complete manuscript.","verification":"unclassified"}],"bibtex":"@article{rajan2026machinelearningg2betti,\n  author = {Rajan, Mayone Maha},\n  title = {Machine Learning G2 Betti Numbers from Orientifold Calabi-Yau Data: A Leakage-Audited Predictive Test},\n  journal = {Maha Strategies Research},\n  year = {2026},\n  version = {2.0.0},\n  url = {https://research.mahastrategies.com/papers/machine_learning_g2_betti},\n  note = {Working paper; not peer reviewed}\n}"}