arXiv 2602.025262026-02cs.LGcs.AIcs.CLphysics.comp-ph

‘罗伯特·布尔顿’奇点：递归AI中的语义隧道与流形展开

The "Robert Boulton" Singularity: Semantic Tunneling and Manifold Unfolding in Recursive AI

Taras Shevchenko National University of Kyiv（基辅塔拉斯·舍甫琴科国立大学）

Pengyue Hou

备注：: Companion paper to arXiv:2601.11594. Provides empirical validation of the MNCIS framework in Large Language Models (GPT-2) using a recursive training protocol (N=1500). Includes complete, reproducible Python implementation of Adaptive Spectral Negative Coupling (ASNC) and Effective Rank metrics in the Appendix

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出MNCIS框架，通过ASNC方法解决递归AI中语义隧道问题，提升流形多样性与语义多样性。

摘要：

生成式人工智能在递归合成数据上的稳定性通常通过困惑度（PPL）来监测。我们证明在上下文稳定区域（L=128）中，PPL是一个欺骗性的指标。使用严格的滑动窗口协议（N=1500），我们识别出一种新的故障模式，称为“语义隧道”。尽管基线模型保持高语法流畅性（PPL约83.9），但它却失去了语义多样性，七代后收敛到单一低熵叙事吸引子：‘罗伯特·布尔顿’奇点。这一现象代表了潜在流形的完全崩溃（全局有效秩3.62→2.22），其中模型为了优化统计安全的语法模板而丢弃了多样的世界知识。为解决此问题，我们应用了最近在Hou（2026）中建立的多尺度负耦合信息系统（MNCIS）框架。我们证明了自适应频谱负耦合（ASNC）作为一种拓扑操作符，主动诱导“流形展开”。MNCIS迫使模型将有效秩从各向异性基线3.62扩展到超多样化的状态5.35，有效地构建了一个“人工流形”，该流形抵抗了语义吸引子的引力并保留了训练数据的长尾分布。

英文摘要：

The stability of generative artificial intelligence trained on recursive synthetic data is conventionally monitored via Perplexity (PPL). We demonstrate that PPL is a deceptive metric in context-stabilized regimes (L=128). Using a rigorous sliding-window protocol (N=1500), we identify a novel failure mode termed "Semantic Tunneling." While the Baseline model maintains high grammatical fluency (PPL approx. 83.9), it suffers a catastrophic loss of semantic diversity, converging within seven generations to a single, low-entropy narrative attractor: the "Robert Boulton" Singularity. This phenomenon represents a total collapse of the latent manifold (Global Effective Rank 3.62 -> 2.22), where the model discards diverse world knowledge to optimize for statistically safe syntactic templates. To address this, we apply the Multi-Scale Negative Coupled Information Systems (MNCIS) framework recently established in Hou (2026) [arXiv:2601.11594]. We demonstrate that Adaptive Spectral Negative Coupling (ASNC) acts as a topological operator that actively induces "Manifold Unfolding." MNCIS forces the model to expand its effective rank from the anisotropic baseline of 3.62 to a hyper-diverse state of 5.35, effectively constructing an "Artificial Manifold" that resists the gravitational pull of semantic attractors and preserves the long-tail distribution of the training data.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。