Skip to content
Hot eventLive

SHAD:时序异常检测、可解释性与可解读性端到端基准

1 reports1 sources5 hr ago updated

Get the story

AI overview

2026-10-02,arXiv 发表 SHAD(Scality High-dimensional Anomaly Detection benchmark)基准,面向分布式云存储系统的多变量高维时间序列异常检测、可解释性与可解读性端到端评测。数据集包含 215 条来自 Scality 系统的序列,覆盖三类异常严重程度,并提供丰富语义标注。评测覆盖现有异常检测器、各维度贡献归因方法,以及冻结 LLM 基线的异常定位与解读效果。

Generated from reports · updated 4 hr ago

Timeline

Follow the coverage from different angles.

Oct 2, 2026
  1. arXiv · Databases
    SHAD 基准:时间序列异常检测、可解释性与可解读性端到端评测

    SHAD(Scality High-dimensional Anomaly Detection benchmark)包含 215 个来自 Scality 分布式云存储系统的多变量高维时间序列,覆盖三类异常严重程度,并提供丰富语义标注。论文对检测、可解释性与可解读性三阶段进行基线评测,包括现有异常检测器、各维度贡献归因以及冻结 LLM 基线的异常定位与解读效果。

Heat trend

Current heat 9·Comparable peak 10(Oct 2)·Comparable change over 24 hours –

02.557.510Oct2Oct2Oct2Oct2

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.