MRiabov/IntersectionQA-90K
收藏资源简介:
IntersectionQA-90K是一个专注于CAD空间推理的代码基准测试数据集。每个示例提供两个可执行的CadQuery对象构建函数及装配变换,要求模型推断代码所诱导的几何关系。核心问题是评估代码模型能否在心理上追踪CAD程序的空间后果,包括体积干涉、接触、接近未命中、间隙、包含和重叠量等。数据集旨在测量代码的闭书几何基础,而非替代CAD内核。官方标签通过CadQuery/OpenCASCADE布尔和距离查询离线生成,存储在行中以便训练和评估无需执行CAD代码。数据集包含90,000个任务行,分为训练、验证和测试集,以及针对边界/反事实案例的挑战套件。
IntersectionQA-90K is a code-only CAD spatial-reasoning benchmark. Each example provides two executable CadQuery object-construction functions plus assembly transforms, then asks the model to infer the geometric relation induced by that code. The central question is whether a code model can mentally track the spatial consequences of CAD programs: positive-volume interference, contact, near misses, clearance, containment, and overlap magnitude. The dataset is not intended to replace a CAD kernel. Official labels are produced offline with CadQuery/OpenCASCADE Boolean and distance queries, then stored in the rows so training and evaluation can run without executing CAD code. The benchmark measures closed-book geometric grounding from code. This release contains 90,000 public task rows, split into training, validation, and test sets, plus named diagnostic suites for boundary/counterfactual cases.




