Adds editorial notes referencing Radhakrishnan et al. (2026) Science paper
to both research paper markdown source files.
STO-RES-0009 v1.1: editorial note after Section 4.1, revised text paragraph,
3 conclusion paragraphs, Radhakrishnan reference added.
STO-RES-0010 v0.2: two editorial notes (after Section 4.1 and before
references), Radhakrishnan reference added, version updated from 0.1 DRAFT.
HTML download files and PDFs already deployed to production.
MongoDB updated with backup in documents_pre_editorial_20260222 collection.
Note: HTML download files not included in this commit due to pre-existing
inline styles triggering CSP hook (standalone download files, not app pages).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Four critique responses integrated:
1. Decolonial framing (§2.1) — name colonial knowledge hierarchies explicitly
2. Sovereignty caveat (§4.3) — two-tier model is stepping stone, not destination
3. Off-limits domains (§6.4) — culturally sovereign knowledge not for platform steering
4. Governance decision-rights table (§6.5) — who steers, with what authority
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Research paper investigating representational vs. reasoning bias in LLMs,
surveying steering vector techniques (CAA, RepE, FairSteer, DSO, SAEs),
and assessing feasibility for sovereign SLM deployments (Home AI).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
