We present CARTOGRAPH, a verification layer for AI scientists that couples unresolved-subspace experiment steering (select), explicit ambiguity closure (resolve), and residual-based library inadequacy detection (refuse). Under a local linear-Gaussian bridge, raw unresolved projection is the isotropic unresolved Fisher-information trace, while CARTOGRAPH-A is the exact unresolved A-optimal rule; closed-form EIG and Box-Hill arise as local comparators rather than global equivalents. Across five testbeds, CARTOGRAPH-A beats raw projection 129W/0T/15L at d = 8 (p < 10^-21) in a replicated structured cascade. More distinctively, the framework tentatively identifies three out-of-library pharmacokinetic mechanisms and then revokes those identifications as residuals expose structural misfit, while one perturbed in-library control stays identified throughout. In low-dimensional pharmacokinetic and filtered EPA settings, near-ties against disagreement are predicted by theory and observed. Finally, in a retrospective audit of 40 positive claims from the published A-Lab autonomous materials system, the refuse guard flags all 4 claims later marked inconclusive under manual reanalysis while passing 32/36 confirmed claims. Code is available at https://github.com/ai4science-boed/cartograph.git

翻译：我们提出CARTOGRAPH——一种面向AI科学家的验证层，该验证层结合了未解析子空间实验引导（选择）、显式歧义闭合（解析）以及基于残差的库不充分性检测（拒绝）。在局部线性-高斯桥接框架下，原始未解析投影量即为各向同性未解析Fisher信息迹，而CARTOGRAPH-A则是精确的未解析A-最优准则；闭式EIG和Box-Hill指标作为局部比较量而非全局等价量出现。在五个测试平台上，经过重复结构级联实验，CARTOGRAPH-A在d=8维度下以129胜/0平/15负（p<10^-21）显著优于原始投影方法。更独特的是，该框架初步识别出三个库外的药代动力学机制，但当残差暴露结构失配时即撤销这些识别结果，而一个经扰动处理的库内对照组始终维持识别状态。在低维药代动力学和滤波EPA场景中，理论预测的对等比较接近与分歧现象均被实验观测到。最后，对已发表的A-Lab自主材料系统中40项阳性声明进行回溯审计时，拒绝保护机制标记了所有4项后续经人工复核被判定为不确定的声明，同时通过了36项确证声明中的32项。代码见https://github.com/ai4science-boed/cartograph.git