用合成数据诊断时序模型能否还原信号细节，发现多数模型只认得类型不认得状态。
Aionoscope: Debugging Latent-State Accessibility in Time-Series Representations
- 构建生成式诊断工具Aionoscope，分离生成与观测，精准控制信号成分和干扰。
- 37个模型系统中，密集状态恢复最高仅0.689均方$R^2$，远低于理想值0.999。
- 适合关注模型可解释性、调试时序信号状态的开发者与研究者使用。
时序模型常以预测或分类性能评估，但这些指标无法反映其表征是否保留用户希望检查的过程状态，如事件时间、相位、振幅、频率或制度变量。本文提出Aionoscope，一种基于生成器的诊断工具，用于调试冻结时序表示中的潜在状态可访问性。Aionoscope将过程生成与观测渲染分离，生成带有精确类别标签和连续标签的种子化合成序列，覆盖混合复杂度和干扰变化。我们以原始过程混合形式实例化Aionoscope，对37个模型-适配器系统采用统一线性探测协议进行评估。主要发现是粗粒度与细粒度可访问性之间的不匹配：大多数系统能轻松恢复组件存在性，但对密集过程状态的恢复却不可靠——最高密集探测得分仅为0.689均方$R^2$，而密集特征最优探针可达0.999。这正是Aionoscope旨在揭示的失效模式：表示在‘存在何种信号’层面看似丰富，实则隐藏了调试所需的时间、相位、振幅、频率或制度变量。
原文摘要 · Abstract (English)
Time-series models are often evaluated by what they can forecast or classify, but those scores do not show whether their representations preserve the process state a user may want to inspect: event timing, phase, amplitude, frequency, or regime variables. We introduce Aionoscope, a generator-based diagnostic tool for debugging latent-state accessibility in frozen time-series representations. Aionoscope separates process generation from observation rendering, producing seeded synthetic streams with exact categorical and dense labels across mixture complexity and nuisance variation. We instantiate Aionoscope as Primitive Process Mixtures and evaluate 37 model-plus-adapter systems with a common pooled linear-probe protocol. The main result is a mismatch between coarse and fine-grained accessibility. Most systems make component presence easy to recover, but expose dense process state much less reliably: the highest observed dense-probe row reaches 0.689 mean masked $R^2$, while a dense-feature oracle reaches 0.999. This is the failure mode Aionoscope is designed to surface: a representation can look informative at the level of "what kind of signal is present" while hiding the timing, phase, amplitude, frequency, or regime variables needed for debugging.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。