R0002 — Research Standards for AI-Assisted Writing¶
Investigation of the frameworks underlying the site's hybrid research standard: intelligence community tradecraft (ICD 203), scientific methodology (GRADE, IPCC, PRISMA, Cochrane, CONSORT, ROBIS, NAS), and the gap between principles-based and methodology-based approaches.
Status: Active
Articles:
A0012 — When the Footnotes Fight Back (Part 1)
In progress · methodology
A0013 — The Prompt (Part 2)
In progress · methodology
A0014 — Describe the Process vs. Constrain the Behavior (Part 3)
In progress · methodology
Runs¶
2026-03-13 — Initial research run
Mode: Claim · Claims: 12 · Prompt: research-standard-claim (full-prompt-run-07) · Model: Claude Opus 4.6
12 claims investigated. Full entity decomposition with search logs, source scorecards, evidence extracts, ACH matrices, and self-audits.
Part of a controlled A/B experiment comparing baseline prompts against the full three-layer research standard (10 runs, 31 of 32 agents completed).