Grand Diomande Research · Full HTML Reader

N'Ko Research Papers

The public closeout series now lives under `final/`. Each paper has its own folder with a local `paper.tex`, compiled `paper.pdf`, `references.bib`, `paper.bbl`, and relative `figures/` assets, so each manuscript can compile from its own directory.

Language as Infrastructure proposal experiment writeup candidate score 30 .md

Full Public Reader

N'Ko Research Papers

Final Four-Paper Series

The public closeout series now lives under `final/`. Each paper has its own folder
with a local `paper.tex`, compiled `paper.pdf`, `references.bib`, `paper.bbl`, and
relative `figures/` assets, so each manuscript can compile from its own directory.

#	Paper	Folder	PDF pages	Role
1	Dead Circuits: Script Invisibility and Representation Failure for N'Ko in Large Language Models	`final/01-script-invisibility/`	11	Establishes the LLM representation failure with research questions, falsification criteria, evidence ladder, tokenizer-burden formalism, evidence artifact contract, remediation agenda, reviewer checklist, and validity threats.
2	Against WER: Phonemic Evaluation, Orthographic Transparency, and the Script Advantage for Manding ASR	`final/02-phonemic-evaluation/`	10	Formalizes the metric problem, N'Ko-vs-Latin script advantage, transparent-script edit preservation, normalization protocol, CER/PER proxy boundary, metric failure taxonomy, and matched-evaluation requirements.
3	Script-Native ASR for N'Ko: Anticipatory Transformer CTC Decoding and the 20.57
4	Anticipation Geometry Partition: Row-Level Governance for Script-Native N'Ko ASR Deployment	`final/04-agp-deployment/`	12	Defines AGP as the post-ASR correction/provenance/deployment governance layer with system boundaries, pipeline formalization, row contracts, partition scoring, correction benchmark design, failure taxonomy, human review, data lifecycle, Djoko substrate, and ExpF/ExpH evidence.

Recommended public narrative: use the four papers as the final publishable bundle
and treat `current/paper_canonical_nko_agp_20cer.tex` as the synthesis manuscript
that explains how the four papers connect. The 20.57
archived N'Ko trajectory ASR checkpoint under recorded settings, not as a universal
matched proof against Latin.

Public Blog Series

The readable public companion lives in `blog-series/`. It inherits the stronger
voice from the original `blog/posts/` drafts: historical opening, experiment
chronology, concrete numbers, and plain-English explanations before acronyms. Start
with `blog-series/00-field-guide-to-the-claim.md`, then publish the four essays in
order.

Current Papers

#	Paper	File	Status	Pages
1	Dead Circuits: Activation Profiling and Script Invisibility in LLMs	`current/paper1_dead_circuits.tex`	Draft complete	~20
2	Living Speech: Script-Native ASR for N'Ko	`current/paper2_living_speech.tex`	Draft complete	~20
3	Script Invisibility Is Structural: Across Three LLM Families	`current/paper3_cross_model.tex`	Draft complete	~12
4	Does Script Design Matter? Phonetic Transparency and CTC Decoding	`current/paper4_script_advantage.tex`	Draft complete	~14
5	Script as Thought: Indigenous Script in Personalized Models	TBD	Experiment C scaffolded	—
6	Inscribing Knowledge: Blockchain Provenance	TBD	Experiments D+E scaffolded	—

Canonical Synthesis

The current synthesis manuscript is `current/paper_canonical_nko_agp_20cer.tex`.
It consolidates Papers 1-5, the April 2026 paper proposals, and the archived
anchor record into one research-grade public narrative around the
20.57
AGP. The current compiled PDF is 29 pages and expands the methods-through-conclusion
arc with an explicit evidence ladder, artifact protocol, data-risk taxonomy,
trajectory-channel formulation, AGP row contract, deployment constraints, and publication
claim boundaries. It also includes a dedicated script-advantage section explaining
N'Ko versus Latin mapping, vowel/consonant codepoint examples, tone/nasalization
marks, and why those properties matter for CTC alignment and CER interpretation.
The related-work frame now expands the WER/CER metric problem and the orthographic
transparency label-unit problem, including scorer-unit requirements and a mapping
ambiguity formulation.
It now places an "Initial Hypothesis Stack" immediately after the introduction,
reconstructing the original project hypotheses and their current evidence status.

See `PAPER_ROADMAP.md` for the full plan, timeline, and dependencies.

Structure

paper/
├── README.md           ← You are here
├── PAPER_ROADMAP.md    ← 6-paper plan with timeline and costs
├── blog-series/        ← Public narrative essays for the final bundle
├── final/              ← Four standalone final papers with local assets
├── current/            ← Active paper drafts
│   ├── paper1_dead_circuits.tex
│   ├── paper2_living_speech.tex
│   ├── paper3_cross_model.tex
│   └── paper4_script_advantage.tex
├── archive/            ← Superseded drafts (kept for reference)
│   ├── main.tex, main_v2.tex, ...
│   └── *.pdf (compiled versions)
├── acl.sty             ← ACL LaTeX style
└── references.bib      ← Shared bibliography

Promotion Decision

Attach run IDs, datasets, metrics, and reproduction commands.

Source Anchor

nko-brain-scanner/paper/README.md

Detected Structure

Method · Evaluation · References · Figures · Architecture