N'Ko Research Paper Roadmap

Six papers forming a coherent research arc: from diagnosing why AI fails on N'Ko, to building systems that work, to proving structural advantages, to connecting language identity with personalized AI and blockchain provenance. Each paper builds on the previous. Together they constitute a thesis-level body of work on indigenous script computing. **Title:** Dead Circuits: Activation Profiling and Script Invisibility in Large Language Models **Status:** Draft complete (1,305 lines). Model identity corrected to Qwen3-8B. Claims audited. **Core finding:** LLMs have zero functional circuits for N'Ko. Translation tax of 2.90x, 0/55 reasoning configurations, 85.8% kurtosis deficit. Three-stage LoRA reduces tax to 0.70x.