The BBDVW Conjecture for Kazhdan-Lusztig polynomials of lower intervals
Grant T. Barkley, Christian Gaetz
TL;DR
This work studies the BBDVW conjecture for Kazhdan--Lusztig polynomials via hypercube decompositions in Bruhat intervals, connecting it to the Combinatorial Invariance Conjecture. It introduces $N_{u,v,I}$, $Q_{u,v,I}$, and the relative $\widetilde{R}$-polynomials $\widetilde{R}_{u,v,I}$, and develops notions of strong hypercube clusters, the numerical criterion, and property (E). By establishing implications between the BBDVW identity and related recurrences under these hypotheses, the authors prove the conjecture for lower intervals $[e,v]$ in the symmetric group, using a refined combinatorial framework (blocks, antichains, camels, caravans). This structural analysis yields a combinatorial pathway to compute $P_{u,v}$ from poset data and strengthens the connection between hypercube decompositions and invariant KL polynomials in a nontrivial interval class.
Abstract
Blundell, Buesing, Davies, Veličković, and Williamson (BBDVW) introduced the notion of a hypercube decomposition of an interval in Bruhat order. They conjectured a recursive formula in terms of this structure which, if shown for all intervals, would imply the Combinatorial Invariance Conjecture of Lusztig and Dyer, for Kazhdan-Lusztig polynomials of the symmetric group. In this article, we prove implications between the BBDVW Conjecture and several other recurrences for hypercube decompositions, under varying hypotheses, which have appeared in the recent literature. As an application, we prove the BBDVW Conjecture for lower intervals $[e,v]$, the first non-trivial class of intervals for which it has been established.
