事件记忆：通过序列模式挖掘与速度分层检索实现免训练操作记忆
原标题：Incident Memory: Training-Free Operational Memory through Sequential Pattern Mining and Velocity-Stratified Retrieval
AI 摘要
arXiv 论文提出 Incident Memory，一种免训练的操作记忆系统，结合速度分层检索、指纹条件 PrefixSpan 挖掘和溯源感知指标定义，从事件日志中提取有序剧本。在 UCI ITSM 数据集上挖掘 39 个剧本，覆盖 84.3% 的保留事件，受控基准下有序精度达 99.2%，优于 Claude Haiku 基线。结果表明，在低熵事件历史中，精确记忆比开放式生成更有效。
正文节选
Incident Memory: Training-Free Operational Memory through Sequential Pattern Mining and Velocity-Stratified Retrieval Abstract Incident response is a memory problem: teams accumulate tickets, traces, postmortems, and wiki pages, but the knowledge needed for the next incident is rarely stored with its order, freshness, and provenance intact. We present Incident Memory, a deterministic system that accumulates operational knowledge without model training. It combines (i) velocity-stratified retriev