发表机构
Anadolu University; ITouch Systems; Mersin University; Toros Science College（安纳多卢大学; ITouch系统公司; 梅尔辛大学; 托罗斯科学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出通用分形自然语言决策图，利用Mandelbrot集混沌边界动态调制坐标种子，实现零显存、低延迟（7.08毫秒）的实时边缘分流，在JevBench上排名世界第一，准确率达92.6%。
AI 中文摘要
在运行时操作分流中部署大型语言模型会带来难以承受的延迟（>100-500毫秒）、高显存需求（>4-8GB）以及过度的能量消耗。本文扩展了Mandelbrot分形神经综合（Dagli等人，2026），提出了通用分形自然语言决策图，通过werr机器原生边缘反射运行时和生产级answerr平台（https://this URL）实现。该引擎完全无需存储权重张量（0字节显存），通过动态调制24字节坐标种子沿Mandelbrot集的混沌边界并评估4象限逃逸动力学，合成确定性决策——noul（布尔）、choice（分类）和score（序数）。受生物系统一型反射弧的启发，该引擎引入了：（i）自动种子路由器，配备域投影器Phi_D，相比线性基线获得+28.8%的准确率提升；（ii）基于令牌熵和语音频谱密度的信息论声学阻尼滤波器，可抵御提示注入（0.0%经验绕过率；95% Wilson置信区间：[0.0%, 30.8%]），同时将逃逸迭代次数削减45.8%（吞吐量加速2.5倍，延迟降至3.31毫秒）；（iii）有机动态校准框架，使用O(1)指数移动平均（EMA，alpha=0.03）和象限相位旋转以消除位置偏差。在裸机基础设施（https://this URL）上对1,150多个已验证决策（3,200多个问题）进行基准测试，并在独立JevBench套件中排名世界第一（81.65%），该框架实现了92.6%的宏平均准确率（95%置信区间：[90.8%, 94.1%]），中位CPU延迟为7.08毫秒。我们提供兼容OpenAI的API（/v1/chat/completions），并展示了在微控制器和32字节EVM智能合约上的可行性。
英文摘要
Deploying Large Language Models for runtime operational triage incurs prohibitive latency (>100-500 ms), high VRAM requirements (>4-8 GB), and excessive energy dissipation. Extending Mandelbrot Fractal Neural Synthesis (Dagli et al., 2026), this paper presents the Universal Fractal Natural Language Decision Map, realized via the werr machine-native edge reflex runtime and the production answerr platform (https://answerr.me). Operating entirely without stored weight tensors (0 Bytes VRAM), the engine synthesizes deterministic decisions---noul (Boolean), choice (categorical), and score (ordinal)---by dynamically modulating 24-byte coordinate seeds along the chaotic boundary of the Mandelbrot set and evaluating multi-scale escape dynamics. Drawing inspiration from biological System-One reflex arcs, the engine introduces: (i) an Auto-Seed Router with domain projector Phi_D yielding a +28.8% accuracy gain over linear baselines; (ii) an Information-Theoretic Semantic Token Damping Filter (T_desc = 0.045) insulating against prompt injections (0.0% empirical bypass; 95% Wilson CI: [0.0%, 27.8%]) while pruning iterations by 45.8% (accelerating throughput 2.5x to 3.31 ms latency); (iii) a Multi-Scale Harmonic Tripod Fusion; (iv) a Coupled Margin Expansion Operator (Pitchfork Bifurcation Offset); and (v) a Cyclic Z/9Z Modular Resonant Grid Discretization based on the closed sub-ideal {0,3,6} (Lean 4 Mathlib ZMod 9), reducing FLOPs by 68.4%. Evaluated on JevBench (N=231), werr achieves 100.00% TypeSafe compliance and 81.65% calibrated accuracy with 7.08 ms median latency. We provide an OpenAI-compatible API and demonstrate deployment on 32-byte EVM smart contracts via the open-source werracle on-chain oracle (21,438 gas).
Comments10 pages, 5 figures. Version 2.0 with expanded EVM on-chain oracle benchmarks (werracle), formal multi-scale tripod dynamics, semantic token damping filter, and Zenodo v2 dataset
