新皇极经世 (Neo Huangji Jingshi): Structural Priors from Ancient Chinese Mathematics — Twelve Laws Verified Through Deep Learning (v6)

v6 update: finalized TCGA counts (20 types), runtime corrections: Added Extended Data Table 1 (TCGA 20-cancer pan-cancer sweep with five-element prior), per-edge bootstrap validation, and updated Discussion. Seven ancient Chinese texts contain mathematical structures that, when translated into neural network architectures, improve performance. 12 laws, 24 experiments, 12/12 validated. Includes Nature-format manuscript (v5, 27 refs, 5 figures), 24 reproducible experiment scripts, 4 reusable Python modules (daoshu), cover letter, reporting summary, and suggested reviewers.