世界需求模型：从类型化工件图学习需求变更后果
原标题：World Requirement Model: Learning Requirement-Change Consequences from Typed Artifact Graphs
AI 摘要
该论文提出 World Requirement Model（WRM），将需求变更的工程上下文编码为带类型的工件图，通过关系感知注意力和类型化传播预测变更影响、冲突、违规与缺陷风险。在六个领域 282 个合成案例中，WRM 在 28 个评分案例上取得 0.724 的 impact MAP，相比哈希文本 MLP 基线提升 16.2%，最低四分位平均 AP 提升 32.4%。作者同时指出检查点基于评分案例选择、骨干网络不匹配等评估局限，并给出候选覆盖边界与线性影响头无法跨决策重排固定世界工件的分析。
正文节选
World Requirement Model: Learning Requirement-Change Consequences from Typed Artifact Graphs Abstract. Requirement changes can affect connected stakeholders, constraints, components, and tests. We present World Requirement Model (WRM), which encodes this engineering context as a typed artifact graph and predicts consequences at shared artifact identifiers. Relation-aware attention and typed propagation contextualize nodes; world and decision representations support learned dynamics. Shared reado