让机器学会判断信息何时过时，像人一样有时间感知。
Chronocept: Instilling a Sense of Time in Machines
- 用连续概率分布建模信息时效性，通过偏正态曲线捕捉变化规律。
- 两个数据集标注一致性高，基线模型在参数预测上优于传统分类方法。
- 适合做知识更新、事实核查、智能代理等需要时间推理的场景。
人类认知与时间感知（称为Chronoception）密切相关，使我们能判断信息的有效时长和过时时间。尽管视觉、语言和运动控制领域进展显著，人工智能仍难以进行时间有效性推理。本文提出Chronocept，首个将时间有效性建模为连续概率分布的基准。通过在语义分解的时间轴上拟合偏正态曲线，Chronocept捕捉信息出现、衰减和峰值相关性的细微模式。包含两个数据集：基准Ⅰ（原子事实）和基准Ⅱ（多句段落），标注显示较高的一致性（84%和89%）。基线模型预测曲线的定位、尺度和偏度参数，实现可解释、泛化性强的学习，优于基于分类的方法。Chronocept填补了人工智能时间推理的基础空白，支持知识定位、事实核查、检索增强生成（RAG）及主动式智能体等应用。代码与数据已公开。
原文摘要 · Abstract (English)
Human cognition is deeply intertwined with a sense of time, known as Chronoception. This sense allows us to judge how long facts remain valid and when knowledge becomes outdated. Despite progress in vision, language, and motor control, AI still struggles to reason about temporal validity. We introduce Chronocept, the first benchmark to model temporal validity as a continuous probability distribution over time. Using skew-normal curves fitted along semantically decomposed temporal axes, Chronocept captures nuanced patterns of emergence, decay, and peak relevance. It includes two datasets: Benchmark I (atomic facts) and Benchmark II (multi-sentence passages). Annotations show strong inter-annotator agreement (84% and 89%). Our baselines predict curve parameters - location, scale, and skewness - enabling interpretable, generalizable learning and outperforming classification-based approaches. Chronocept fills a foundational gap in AI's temporal reasoning, supporting applications in knowledge grounding, fact-checking, retrieval-augmented generation (RAG), and proactive agents. Code and data are publicly available.
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。