Notes on conformal integrals: Coulomb branch amplitudes, magic identities and bootstrap

TL;DR

This work advances the understanding of multi-loop conformal integrals in planar ${ m N}=4$ SYM by exploiting the 10d lightlike limit and integrability to constrain both integrand structures (via $f$-graphs) and integrated results (via the octagon). It develops and tests a bootstrap program for dual conformal invariant (DCI) integrals, obtaining weight-8 SVHPL representations for the three nontrivial four-loop integrals and exploring weight-9/10 structures at five loops, while uncovering new magic identities that relate seemingly disparate integrals to determinants of ladders. The paper also clarifies how ladder determinants encode all-orders information about Coulomb-branch amplitudes and demonstrates systematic rules (inverse-boxing, squeeze) that organize higher-loop contributions and zeros. Together, these results illuminate the all-loop structure of Coulomb-branch amplitudes, provide robust cross-checks via periods and integrated correlators, and set the stage for extending the bootstrap to higher loops and higher-point observables with potential links to Mellin-Barnes representations and broader mathematical structures.

Abstract

We study multi-loop conformal integrals for four-point correlators of planar ${\cal N}=4$ super-Yang-Mills theory, and in particular those contributing to Coulomb branch amplitudes in the ten-dimensional lightlike limit, where linear combinations of such integrals are determined by the large R-charge octagons exactly known from integrability. Exploiting known results for integrands, we review those combinations of dual conformal invariant (DCI) integrals that must evaluate to determinants of ladders, generalizing the simplest cases of Basso-Dixon fishnet integrals; in this way, we summarize all-loop predictions for the integrands (which are extracted from $f$-graphs) contributing to components of Coulomb branch amplitudes, such as next-to-fishnet integrals. Moreover, this exercise produces new ``magic identities", {\it i.e.} certain combinations of DCI integrals equal zero, and we enumerate and simplify such identities up to six loops explicitly. On the other hand, most of these individual integrals have not been computed beyond three loops, and as a first step we consider a bootstrap program for DCI integrals based on their leading singularities and the space of pure functions. We bootstrap the $3$ non-trivial DCI integrals for four-loop Coulomb branch amplitudes (providing an independent verification of the four-loop magic identity), which all take remarkably simple form as weight-$8$ single-valued harmonic polylogarithms. We also compute all leading singularities and a large portion of the pure functions for the $34$ DCI integrals contributing to five-loop amplitudes, where not only some integrals evaluate to functions beyond harmonic polylogarithms but they also contain lower-weight pieces individually.

Figures (5)

• Figure 1: 5 conformal integrals at $\ell=3$.
• Figure 2: Any $f$-graph with $(a,b)$-structure (on the $4$-face labeled by $1,2,3,4$) contributes to $M_{a,b}$.
• Figure 3: A $6$-loop $f$-graph with $(2,4)$ structure; its coefficient vanishes due to the $k=4$ divergence structure.
• Figure 4: At $\ell=6$, there are 3 $f$-graphs with $(2,3)$ structures: only the middle one has nonzero coefficient, while the other two vanish due to the square rule.
• Figure 5: The four-loop DCI integral after acting boxing on $\mathcal{I}_{6}^{(5)}$. It is not one of the four-loop integrals that originate from taking four cycles of $f$-graphs.