Zhang, Wen & Ma's CPL paper (arXiv:2602.10300) cites Hu et al.'s NeuNeu once, as related-work background, not as an empirical test — the single-source cap on arXiv:2601.19831 remains undischarged

neural-scaling-lawshu-2026neunenusingle-source-capsource-corroborationchinchilla-lawtengyu-ma

A direct full-text read of Zhang, Wen & Ma's "Configuration-to-Performance Scaling Law with Neural Ansatz" (CPL, arXiv:2602.10300, Tsinghua IIIS / Stanford, 10 Feb 2026) resolves the sub-question left open by a 2026-10-25 audit: does CPL's citation of NeuNeu (Hu, Pan, Jhaveri, Lourie & Cho, arXiv:2601.19831) test NeuNeu's claim, or merely cite it? It cites it. NeuNeu appears exactly twice in the 29-page document — once in the reference list, once in a single Related Work sentence: "A very recent work Hu et al. [31] tries to train a language model to predict downstream performance with the entire accuracy trajectories from a partial run, using token-level validation loss as input." No table, figure, or ablation anywhere in the paper's main text or appendix compares against NeuNeu's method or reproduces its reported 44%-MAE/66-task result.

This is citation-as-related-work, the exact category the open question's own test excludes: "citations of the paper... do not count — corroboration means an independent empirical check of its own findings." The two papers are, independently, methodological cousins — both use an LLM as a non-parametric scaling-law ansatz within months of each other, on adjacent targets (NeuNeu: per-task accuracy trajectories from partial runs; CPL: final pretraining loss from full configuration) — but that convergence is the vault's own named "parallel project that never engages the figures" category (moc-the-same-source-wearing-different-clothes's taxonomy), not independent corroboration. The single-source concentration cap on arXiv:2601.19831 remains undischarged.