发表机构
School of Intelligent Systems Engineering, Sun Yat-sen University; Shenzhen 518107, China（中山大学智能工程学院; 中国深圳）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出广度学习概念，形式化学习器的有效认知触及范围，通过受控构造证明学习可在原始可供性与资源固定时改变该范围，为学习系统评估提供了新维度。
AI 中文摘要
机器学习通常在证据接口已确定后进行评估，数据集、传感器套件、查询语言、动作集或实验协议决定了可获取的观测结果，学习效果由其从这些观测中提取的内容来评判。我们研究一种互补能力：即使原始可供性保持固定，学习器的状态也可决定其在有限资源下能可靠实现哪些产生证据的实验。我们将这种与学习器相关的实验族称为其有效认知触及范围，并将与任务相关的、由学习引起的该范围变化称为广度学习。我们针对学习器状态、部署预算、可靠性阈值和评估分布，对有效触及范围进行了形式化。在一项受控构造中，两个隐藏世界具有完全相同的公共观测规律，在固定的五原始基元中存在一个有信息量的诊断。校准前，一次地址尝试实现该诊断的概率最多为2^-10 = 1/1024，低于预先指定的0.95阈值；校准后，保留样本的实现概率为1。公共通道的总变差为0，而实现的诊断总变差为1，密封二元风险从约1/2变为0。该构造表明，即使原始可供性和部署资源保持固定，学习也能改变有效认知触及范围，它为学习系统提出了一个互补的评估问题：不仅要评估它们从可用证据中推断出什么，还要评估经验使它们能触及哪些有信息量的证据。
英文摘要
Machine learning is usually evaluated after an evidence interface has been fixed. A dataset, sensor suite, query language, action set, or experimental protocol determines which observations can be obtained, and learning is judged by what it extracts from them. We study a complementary capability. A learner's state can determine which evidence-generating experiments it can reliably realise under bounded resources, even when primitive affordances remain fixed. We call this learner-relative experiment family its effective epistemic reach, and use Wide Learning for task-relevant learning-induced changes in that family.We formalise effective reach relative to learner state, deployment budget, reliability threshold, and evaluation distribution. In a controlled construction, two hidden worlds have exactly the same public observation law. An informative diagnostic exists in a fixed five-primitive substrate. Before calibration, one address attempt realises it with probability at most $2^{-10} = 1/1024$, below a pre-specified 0.95 threshold; after calibration, held-out realisation is 1. Public-channel total variation is 0, whereas the realised diagnostic has total variation 1, and sealed binary risk moves from approximately 1/2 to 0. The construction establishes that learning can change effective epistemic reach even when primitive affordances and deployment resources are held fixed. It opens a complementary evaluation question for learning systems: not only what they infer from available evidence, but what informative evidence experience teaches them to bring within reach.
