arXivFerran Hernandez Caralt, Simon Heilig, Adrián Bazaga, Asja Fischer, Moshe Eliasof, Pietro LiòFri, Oct 2, 2026, 9:37 AM PDT
score 15.1
New test framework verifies benchmarks that claim to measure long-range graph learning
Original: Get a GRIP, this will be a long TRIP: A Quantifiable Long-Range Framework for Verifying Over-squashing
Source: arxiv.org ↗
Writing ELI5 summary…