From 51bc7d88cfb7110417cfe71191aa8f2a8dbaa49d Mon Sep 17 00:00:00 2001 From: David Keane Date: Thu, 30 Apr 2026 18:31:55 +0100 Subject: [PATCH] docs: add README for docs/ folder Matches the README pattern used across other top-level folders (modelfiles, observations, paper, etc.). Provides examiners with a quick entry point into the documentation: what each file is, recommended reading order, and why these docs exist alongside the primary research artefacts. Co-Authored-By: Claude Opus 4.7 (1M context) --- docs/README.md | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) create mode 100644 docs/README.md diff --git a/docs/README.md b/docs/README.md new file mode 100644 index 0000000..7cb33ef --- /dev/null +++ b/docs/README.md @@ -0,0 +1,23 @@ +# Documentation — Research Context & Project Journey + +Curated documentation that supports the CyberRanger CA1 thesis. Includes the complete version evolution, mirrored research blog posts, and an index linking back to the live blog. + +## What's Here + +| File / Folder | Description | Read Time | +|---|---|---| +| [`version-evolution.md`](./version-evolution.md) | **Complete V1 → V43 journey** across 6 eras — Genesis, Exploration, Refinement, Production Hardening, Architecture Maturation, QLoRA Validation. 40+ versions documented with quick-reference table, per-version detail, and key-lessons-by-era summary. Used as Appendix C in the CA1 paper. | 15 min | +| [`research-blog.md`](./research-blog.md) | Curated index of 6 research blog posts with both live URLs and offline-mirror links. Citation format included for academic reuse. | 3 min | +| [`blog/`](./blog) | Offline mirrors of 6 research blog posts (point-in-time snapshots). The live blog at https://davidtkeane.github.io is the canonical source; these copies are frozen for academic record. | — | + +## Recommended Reading Order + +1. **Start here:** [`version-evolution.md`](./version-evolution.md) — gives the full journey from dental chatbot (V1) to QLoRA-validated production model (V42-gold-wrapped) in 15 minutes. +2. **Then:** [`research-blog.md`](./research-blog.md) — index page that points to the underlying experimental write-ups. +3. **Deep dive:** [`blog/2026-03-08-from-rangerbot-to-cyberranger-v42-the-full-story.md`](./blog/2026-03-08-from-rangerbot-to-cyberranger-v42-the-full-story.md) — long-form narrative of the same journey. + +## Why These Docs Are Here + +The Modelfiles, training data, and evaluation scripts are the primary research artefacts. The documents in this folder provide the **interpretive layer** — the journey, the failed iterations, the regressions, the breakthroughs — that transforms 86 Modelfiles into a coherent research story. + +For examiners, this is the fastest path into the project without reading every Modelfile.