✎ Edit this page

Plan: AI-intervention study

Draft, 2026-11-13 · Status: Planned, not frozen · Owner: NT

Preregistration. This plan becomes binding when it is marked Frozen with a date and commit, before the first intervention is published. After that, changes go in LOG.md as dated deviations with reasons. The point is that nobody can say we chose the metric after seeing the results.

The benchmark format, the OpenRouter runner, the search-call logging and the intervention log are designed in buddhist-bench (docs/intervention-study.md at c8fb3d9). This plan does not repeat that design. It fixes the questions, hypotheses and analysis that the design will be used for.

Question

When reliable information about a specific Buddhist text, as taught by specific traditions, is newly published on the open web:

  1. Do models’ answers about that text improve?
  2. How long after publication does any change appear, per model?
  3. Which models call web search for these questions, and when do they find and cite the new pages?
  4. Which kinds of intervention (site, language, format) move answers most?

Hypotheses

What would count against them

Method (outline; details in the buddhist-bench design)

Metrics (headline fixed at freeze)

Not in scope

Risks and ethics

Open decisions before freezing

✎ Edit this page · History · Discuss