Paperlane

no. 15 · Monday 16 November 2026

Machine learning the arithmetic of Boyd's Mahler measure conjectures

Alberto Alfarano, Pablo Bianucci, Matilde N. Lalín and Berend Ringeling

math.NT · v2 · 33 pp

Abstract

Boyd conjectured that the Mahler measure of $P_k(x,y)=x+y+\frac{1}{x}+\frac{1}{y}+k$ for $k$ an integer, is given by $r_kL'(E_k,0)$, where $E_k$ is the elliptic curve associated to the zero locus of $P_k$ and $r_k$ is a rational number. We study various arithmetic properties of $r_k$ using a dataset containing the first $250{,}000$ values of $k$, combining large-scale statistical analysis assisted by \textsc{Claude} with transformer-based experiments carried out using Axolver. We recover Boyd's observation that, apart from a few exceptions, $r_k$ is the reciprocal of an integer. The size of this integer is governed by the conductor of the elliptic curve. Moreover, its $p$-adic valuations display markedly different behavior according to the prime. For $p\geq5$, the observed frequencies of $v_p(r_k)=-m$, for $m\geq1$, are close to $p^{-m}$. At $p=5$, the agreement improves substantially when we restrict to curves with good reduction at $5$. For the primes $2$ and $3$, however, we find additional arithmetic structure involving congruence conditions on $k$ and the primes of bad reduction of $E_k$. Although the neural networks do not predict $r_k$ exactly, they recover significant information about its magnitude and valuations. In particular, the experiments at the prime $2$ suggest predictive relationships within the computed range that are not fully captured by the explicit predictor obtained from our statistical analysis.

comments
33 pages, 19 figures
journal
J. Math. Artif. Intell. 1 (2026), Art. 2, pp. 1-39
fields
Number Theory
pdf ↗ page arXiv:2608.00615 ↗