发表机构
Morgan State University（摩根州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出互补特征域理论，证明信息保持不等于预测贡献保持，通过贡献缺陷量化重编码影响，并借助ECG实验验证了可逆变换改变预测准确性的机制。
AI 中文摘要
互补特征域（CFD）理论将预测价值刻画为一个由表示及其实现族共同诱导的、以上下文为索引的贡献系统。我们证明，香农信息保持并不意味着该贡献系统的保持：在受限决策族下，一个可逆的表示变换可以在保持目标信息不变的同时改变预测贡献。我们通过一个CFD贡献缺陷来形式化由此产生的转变，该缺陷衡量在受控重编码下上下文贡献的变化。对于有界Lipschitz效用，我们证明每个联盟效用偏移受重编码前后可达动作集之间的行为距离限制；因此，每个上下文贡献缺陷受相应联盟不相容性之和的限制。精确的行为封闭性产生不变性，而日益精确的补偿则产生恢复性。一个受控的心电图（ECG）实验说明了这一机制：一个非线性双射重编码保持了冻结时频表示中的信息，但在固定仿射学习器下改变了准确性；应用精确的逆变换则恢复了所有测试的联盟准确性。该结果将信息保持与依赖于实现的贡献分离开来，并为多表示预测提供了定量的转变规律。
英文摘要
Complementary Feature Domains (CFD) theory characterizes predictive value as a context-indexed contribution system induced jointly by representations and their realization family. We show that Shannon-information preservation does not imply preservation of this contribution system: an invertible representation transformation can leave target information unchanged while altering predictive contribution under a restricted decision family. We formalize the resulting transition through a CFD contribution defect that measures how contextual contributions change under controlled recoding. For bounded Lipschitz utility, we show that each coalition utility shift is bounded by the behavioral distance between the attainable action sets before and after recoding; consequently, every contextual contribution defect is bounded by the sum of the corresponding coalition incompatibilities. Exact behavioral closure yields invariance, while increasingly accurate compensation yields restoration. A controlled ECG experiment illustrates the mechanism: a nonlinear bijective recoding preserves the information in a frozen time-frequency representation but changes accuracy under a fixed affine learner; applying the exact inverse restores all tested coalition accuracies. The result separates information preservation from realization-dependent contribution and provides a quantitative transition law for multi-representation prediction.
