Pre-registration of a replication of the neural scaling exponent claim of Kolmogorov-Arnold Networks (arXiv 2404.19756, Sec. 3.1, Fig. 3.1)

Frozen pre-registration (1 Nov 2026) of a private replication of the claim that KANs trained with LBFGS and grid extension reach a test-RMSE-versus-parameter-count exponent close to 4 on smooth toy functions where MLPs do clearly worse (Liu et al., arXiv 2404.19756; code KindXiaoming/pykan, commit ecde4ec3). Four scored functions, a pre-registered training-success gate with the success rate reported, 40 seeds per function, pre-set bounds (KAN slope lower bound 3.0; KAN minus MLP slope above 1.0), known-answer and negative controls. Contains the decision code, harness, power note, planted-effect table and the run kernel. Deposited before any confirmatory run. Outcome wording: Replicated / Did not replicate / Inconclusive under protocol X.