v0.7: Add Research Radar templates and watchlist

[t3chn]

Summary:

• Adds a public-safe Research Radar layer for benchmark/eval methodology monitoring.
• Adds prioritized watchlists, source map, repo/team lists, and query sets.
• Adds daily brief, weekly synthesis, and reading queue templates.
• Adds docs explaining cadence, public/private boundaries, action categories, and roadmap decision flow.
• Updates README and docs index links.

Non-goals:

• no new benchmark task family;
• no automation scripts;
• no scheduled jobs;
• no web scraping;
• no private eval material;
• no hidden holdouts, answer keys, customer data, private rubrics, or protected scorer configs;
• no personal/private notes;
• no consumer product coupling.

Test plan:

• make validate
• make test
• make leak-check
• python3 -m ruff check .
• git diff --check

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: c42cc42813

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

Avoid secret-pattern trip in source map URL

The new NIST URL contains the substring sk-management-framework, which matches the leak checker’s secret regex sk-[A-Za-z0-9_-]{20,} in scripts/public_leak_check.py and causes make leak-check / python3 scripts/public_leak_check.py . to fail on this commit. This turns the newly added documentation row into a deterministic CI/public-release gate failure, so the URL or leak-check handling needs to be adjusted.

Useful? React with 👍 / 👎.