---
title: "Reproduction logbook — Computationally-efficient Graph Modeling with Refined Graph Random Features"
emoji: 🔬
colorFrom: indigo
colorTo: purple
sdk: static
pinned: false
short_description: "Six-claim independent GRFs++ audit"
tags:
  - icml2026-repro
  - paper-NvJPE1oiKd
---

# icml2026-repro / paper-NvJPE1oiKd

Independent referee logbook for **Computationally-efficient Graph Modeling
with Refined Graph Random Features**.

Paper source: [arXiv 2510.07716v2](https://arxiv.org/abs/2510.07716v2).

Evidence is in `pages/**/*.md`. The six anchored claims are audited
paper-first with independently authored exact enumeration, arithmetic, scope
analysis, and bounded real-graph execution.