SOURCE-LINKED INTELLIGENCE

An Exploratory Replica-Overlap Probe of the Grokking Transition

arXiv · AI, language, vision and robotics · article · Sep 22, 2026 · UTC

We trained 64 independently seeded networks in four configurations, continuing each to sustained convergence or a 40,000-epoch ceiling. We then asked whether an RSB-inspired distribution of pairwise weight overlaps changes across the grokking transition. It is the alignment step, not the overlap statistic, that determines what this registered probe can report. The registered implementation permutes hidden units without the corresponding bias and head-internal permutations and therefore does not preserve the network function. Every q_wt value computed through this alignment inherits the defect;

Read original source ↗ Open in workspace

recordType

paper

region

Global