Explainable AI for Mathematics: Proofs as Code with Knowledge Graph and Domain Ontology Support
Mathematics & AI · 22.05.2026 · 1 (2)
DOI: 10.66693/mathai.1020 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics & AI, online erschienen am 22.05.2026. Verfasst von Oli Ataeva und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
We investigate whether structured knowledge retrieval from a mathematical library's dependency graph can improve neural theorem proving at inference time while maintaining explainability of the retrieved context. Through a controlled ablation study on the miniF2F-Test benchmark (197~tasks, 8~non-chain-of-thought modes, $K{=}8$ attempts per mode), we find that graph-based retrieval augmentation significantly improves proof generation on hard problems -- those where the base model's parametric knowledge is insufficient -- while having no measurable effect on problems the model already solves reliably. On 109~hard tasks, the best graph-augmented mode nearly triples the baseline success rate (pass@1: $3.56\% \to 10.42\%$, $+6.8$~percentage points, $p{=}0.001$, Wilcoxon signed-rank test). Deterministic pattern-based graph entry points outperform LLM-generated ones ($11\times$ faster, higher accuracy). The retrieved graph context is fully traceable: each hint maps to a specific edge in the Mathlib dependency graph, enabling the user to verify \emph{why} particular lemmas were suggested. The approach is training-free, composable with any base prover, and adds negligible computational overhead.
Zitieren
APA
Ataeva, O., A., K., & N., T. (2026). Explainable AI for Mathematics: Proofs as Code with Knowledge Graph and Domain Ontology Support. Mathematics & AI, 1(2). https://doi.org/10.66693/mathai.1020
Vancouver
Ataeva O, A. K, N. T. Explainable AI for Mathematics: Proofs as Code with Knowledge Graph and Domain Ontology Support. Mathematics & AI. 2026;1(2). doi:10.66693/mathai.1020
BibTeX
@article{Ataeva2026,
author = {Ataeva, Oli and A., Khalov and N., Tuchkova},
title = {Explainable AI for Mathematics: Proofs as Code with Knowledge Graph and Domain Ontology Support},
journal = {Mathematics & AI},
year = {2026},
volume = {1},
number = {2},
doi = {10.66693/mathai.1020}
}
EUVIMED