arXiv：cs.AI· Lingsen You, Yujun Guo, Xinyu Zhong, Zisu Peng, Wentong Wang, Li Shen, Junbo Ge·· 3 小时前
合成血管预测表征中的干预锚点与科学验证
Intervention anchors and scientific verification in synthetic vascular predictive representations
AI 导读
一项数学与合成审计表明，完整正交预测坐标本身并不能将潜在方向绑定到具名干预：在容量匹配的最小二乘预测器下，6 种三维配置、64 个随机种子给出的最大配对预测差异仅 6.7e-15，但未传输编辑的中位误差达 1.513，坐标传输可消除该误差。
正文
Abstract:Complete orthogonal predictive coordinates do not by themselves bind a latent direction to a named intervention. We present a mathematical and synthetic audit motivated by vascular device-vessel suitcordance. Capacity-matched least-squares predictors were exactly equivalent under complete fixed output transforms, whereas an anchor-only observer recovered interpretations only within the span of known perturbation signatures. Six three-dimensional configurations across 64 seeds gave a maximum paired prediction discrepancy of 6.7e-15 but a median untransported edit error of 1.513. Coordinate transport removed that error. Noisy and weak anchors constrained calibration stability, and changing the representation basis required recalibration or verified transport. Across 256 additional fits in dimensions 3-24, prediction equivalence persisted within 4.0e-15. We then evaluated nine deliberate runnable fault classes across 64 seeds. All 576 faulty executions completed, but each violated at least one reconstruction, prediction, delivered-edit or scope contract; all 320 valid control records passed. Repeating a faulty implementation gave exact self-agreement despite error against the separately computed simulator expectation. For one omitted-direction defect, probe coverage followed its analytic law, and rank-aware abstention protected unsupported interpretations. Scalar-noise experiments exposed both missed weak faults and excessive rejection under narrow relative tolerances. These controls provide an executable separation of prediction, semantic support and scientific acceptance. They are synthetic numerical audits, not clinical validation, neural JEPA-Anything replication, agent learning or patient treatment-effect estimation.
| Comments: | Technical Note; 18 pages, 8 figures; reproducibility source and data archive included |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.11704 [cs.AI] |
| (or arXiv:2610.11704v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11704 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Junbo Ge [view email]
[v1]
Thu, 8 Oct 2026 11:10:56 UTC (1,899 KB)
来源：arXiv：cs.AI · arxiv.org