# A penalised Saito functional for heuristic search of free line arrangements

arXiv: https://arxiv.org/abs/2604.02995 · HTML: https://mlsanity.com/paper/2604.02995/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 38 references that are in the map.
- First posted on arXiv 3 Apr 2026.

## Builds on (most cited first, 5 of 5)

- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [Quality and Diversity Optimization: A Unifying Modular Framework](https://mlsanity.com/paper/1708.09251/) (2017)
- [Machine-Learning Mathematical Structures](https://mlsanity.com/paper/2101.06317/) (2021)
- [Searching for ribbons with machine learning](https://mlsanity.com/paper/2304.09304/) (2023)
- [Neural and numerical methods for G2-structures on contact Calabi-Yau 7-manifolds](https://mlsanity.com/paper/2602.12438/) (2026)

## Abstract (arXiv)

We introduce the penalised Saito functional mathfrak Sλ,β(A;d1,d2) for a reduced arrangement A of n lines and a prescribed pair d1+d2=n-1. It measures the alignment of a candidate Saito determinant with the defining polynomial while penalising the failure of the candidate derivations to be logarithmic. We prove that the functional takes values in [0,1], vanishes exactly when A is free with exponents (1,d1,d2), and lies strictly between 0 and 1 otherwise. For fixed (d1,d2), it is upper semicontinuous on the reduced configuration space, continuous at arrangements free with the prescribed pair, and converges as λ→∞ to the corresponding binary freeness test. We use a numerical approximation of this functional, together with a small b2-shell term, to guide fixed-cardinality line-replacement searches over mathbbQ and selected quadratic extensions. Numerical values are used only to select candidates; every reported arrangement is certified in exact arithmetic using Saito's criterion. At the current snapshot, the certified database contains 6,146 representatives with distinct Weisfeiler--Leman fingerprints and cardinalities up to n=28. Among them, 3,012 have multiplicity gap ε(A)=d1-m(A)≥2, including lower-bound-extremal examples with ε=7. These non-supersolvable arrangements provide test cases for studying realisation spaces and the persistence of freeness among realisations of the same intersection lattice, in connection with Terao's conjecture.