发表机构
Alibaba Group; Xiaomi; University of Electronic Science and Technology of China; University of Bristol; University of California, Irvine; University of Pennsylvania（阿里巴巴集团; 小米; 电子科技大学; 布里斯托大学; 加州大学尔湾分校; 宾夕法尼亚大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TIMBRE通过源感知表示、状态条件响应迁移和可靠性引导融合提升事件信息感知的时间序列预测，在13个任务中较普通融合有改善，但优势有限且依赖响应迁移机制。
AI 中文摘要
事件信息感知的预测需要将报告和历史响应转化为数值预测的变化。我们提出TIMBRE（基于记忆响应与证据的时间整合），它在冻结的预测头之前结合了源感知表示、状态条件响应迁移和可靠性引导融合。一个独立的读出模块在保持中位数的同时调整区间宽度。在包含13个任务的单种子、单周期开发研究中，TIMBRE在八个任务上相较于普通融合提升了MAE，但相较于原生Chronos-2仅在两个任务上有所提升。在训练好的模型中禁用响应迁移分别使BTC和AULF的MAE降低了47.04%和6.81%。这些发现表明其敏感性源于学习到的响应迁移，而非普遍的预测优势。开发集分数的缺失以及未重新训练的消融实验限制了对各证据机制的归因。
英文摘要
Event-informed forecasting requires translating reports and historical responses into changes to a numerical forecast. We propose TIMBRE (Temporal Integration of Memory-Based Responses and Evidence), which combines source-aware representation, state-conditioned response transfer, and reliability-guided fusion before a frozen forecast head. A separate readout adjusts interval widths while preserving the median. In a single-seed, one-epoch development study of 13 tasks, TIMBRE improves MAE over ordinary fusion on eight tasks but over native Chronos-2 on only two. Disabling response transfer in the trained model reduces BTC and AULF MAE by 47.04% and 6.81%, respectively. These findings identify sensitivity to learned response transfer rather than a general forecasting advantage. Missing development-set scores and the absence of retrained ablations limit attribution to individual evidence mechanisms.
Comments5 pages, 3 figures, 4 tables. Code: https://github.com/stephen-guan-researcher/TIMBRE ; Checkpoints: https://huggingface.co/XinyuGuan/TIMBRE
