发表机构
Shanghai Jiao Tong University; Shanghai AI Laboratory（上海交通大学; 上海人工智能实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对基因组尺度代谢模型修复的多对一结构问题，提出QuotientPO将等价修复归为典型机制并在商空间优化探索，在2212个GEM上提升了Success@32并增加了独特成功核心的发现数。
AI 中文摘要
从功能观测修复科学模型与监督预测存在根本差异：反馈可确认解决方案，却不揭示具体是哪项结构修正起作用。本文针对基因组尺度代谢模型（GEM）修复研究该场景，其中多种反应编辑可解释相同表型，且诸多看似不同的编辑对应同一生物学机制。这种多对一结构为传统探索带来隐藏失效模式：输出空间的多样性未必转化为科学假说的多样性。我们提出QuotientPO，它将等价修复归约为典型机制，并直接在所得商空间上优化探索。为使有限滚动下的商空间探索具备信息性，我们推导了核化Rényi估计器，其能区分不同修复核心的分级拥挤度，而非仅依赖粗略的精确匹配计数。在2212个保留的GEM上，QuotientPO将Success@32从17.93%提升至20.10%（相对提升12.1%），同时在相同采样预算下持续增加独特成功核心的发现数量。这些结果表明，商空间探索是在验证器诱导等价性下开展机制层面发现的原则性方法。
英文摘要
Repairing scientific models from functional observations differs fundamentally from supervised prediction: feedback may certify a solution without revealing which structural correction is responsible. We study this setting for genome-scale metabolic model (GEM) repair, where multiple reaction edits can explain the same phenotypes and many apparently distinct edits correspond to the same biological mechanism. This many-to-one structure creates a hidden failure mode for conventional exploration: diversity in the output space need not translate into diversity of scientific hypotheses. We introduce QuotientPO, which collapses equivalent repairs into canonical mechanisms and optimizes exploration directly over the resulting quotient space. To make quotient exploration informative under finite rollouts, we derive a kernelized Rényi estimator that resolves graded crowding among distinct repair cores beyond coarse exact-match counts. On 2,212 held-out GEMs, QuotientPO improves Success@32 from 17.93% to 20.10% (+12.1% relative) while consistently increasing distinct successful-core discovery under the same sampling budget. These results establish quotient-space exploration as a principled approach to mechanism-level discovery under verifier-induced equivalence.
CommentsUnder Review
