We decompose an evolutionary mixture-of-LoRA system on a from-scratch ~150M-parameter widened-D substrate (D=1536, V=32000; D/V approx 0.048; the "widened-1536" substrate) into three factors -- a router rewrite (parallel sigmoid gate with learnable per-adapter floor and bounded temperature anneal, fed post-stack hidden states rather than token-embedding means), a per-domain leave-one-out evaluation scope, and a lifecycle of death plus alpha-blend inheritance plus SVD mutation plus slot reallocation -- and report a 5-of-8 partial 2^3 factorial run at n=3 seeds and 25000 adaptation steps per cell. The attribution chain is sharp on this substrate: the router rewrite carries the entire +0.0426 nat balanced log-PPL improvement (Delta = log PPL_ref - log PPL_test, positive = improvement; t=12.86, p=0.006) attributed to "the full evolutionary system vs the static B3 baseline"; the headline full-system-vs-B3 balanced contrast itself is +0.015 nats, t=1.94, p=0.19 at n=3 and does not clear alpha=0.05. The per-domain evaluation scope is null at seed-resolution, and the lifecycle is a net drag of approx -0.028 nats (t=-4.46,p=0.047 in the primary chain). An auxiliary alpha=0 inheritance counterfactual at n=3 seeds is sign-inconsistent at the headline metric and underpowered for either an equivalence or load-bearing conclusion (corrected from an earlier arithmetic-mean aggregator that erroneously cleared inheritance; see Appendix B.11). A base-perturbation probe directionally refutes a "genomic-context" reframe of the lifecycle role. A controllable synthetic sandbox locates a substrate-conditional regime boundary: evolutionary search on the routing channel is load-bearing only when adapters are pre-aligned to the task; in every other regime tested it underperforms, ties, or actively degrades the gradient solution.

翻译：我们在一个从头训练的约1.5亿参数扩宽D基底（D=1536, V=32000; D/V≈0.048; “扩宽-1536”基底）上，将进化式混合LoRA系统分解为三个因子——路由重写（并行Sigmoid门控，带有可学习的每适配器阈值和有界温度退火，输入为后堆栈隐藏状态而非词嵌入均值）、每域留一评估范围，以及包含消亡、Alpha混合继承、SVD突变和插槽重分配的生命周期——并在n=3个种子和每单元25000步自适应条件下，报告了8次中的5次部分2^3因子设计实验结果。在该基底上，归因链清晰：路由重写承载了归因于“完整进化系统vs静态B3基线”的全部+0.0426 nat平衡对数困惑度改进（Delta=log_PPL_ref - log_PPL_test, 正值表示改进；t=12.86, p=0.006）；而标题性的“完整系统vs B3”平衡对比本身为+0.015 nat（t=1.94, p=0.19, n=3），未达到α=0.05显著性水平。在种子分辨率下，每域评估范围效果为零；生命周期则构成约-0.028净拖累（主链中t=-4.46, p=0.047）。一项辅助性α=0继承反事实实验（n=3种子）在标题指标上符号不一致且统计效力不足，既无法得出等价性结论也无法得出支撑性结论（已从先前错误达到显著性阈值的算术均值聚合器中修正；见附录B.11）。一项基础扰动探针定向反驳了将生命周期角色重构为“基因组上下文”的解读。一个可控合成沙箱定位了基底条件性体制边界：当且仅当适配器与任务预对齐时，路由通道上的进化搜索才具有支撑作用；在所有其他测试体制中，它表现劣于、持平或主动劣化梯度解。