Files
hermes-brain/ideas/passepartout-economics/gate-rule-encoding.org
Hermes 303e8c6306 Convert cross-references from [[id:uuid]] to [[file:name.org]]
All 117 inter-node links now use [[file:node-name.org][title]] format
which renders as clickable hyperlinks in both Emacs (C-c C-o) and
web-based org renderers (Gitea, GitHub). Each node retains its :ID:
UUID property for Emacs org-roam database features (backlinks,
capturing, node-find).

Prev format: [[id:uuid][title]] — Emacs only, dead text on web
New format:  [[file:name.org][title]] — works everywhere
2026-05-21 19:40:54 +00:00

1.4 KiB

Gate Rule Encoding from Codified Domains

Laws, regulations, standards, procedures, and technical specifications are already written down in structured text. The LLM does not need to reason about them — it needs to translate them into gate rules and ACL2 theorems.

Example: The US Federal Acquisition Regulation (FAR) is ~2,000 pages. A frontier LLM can ingest the FAR and produce a plist of gate rules:

  • (if contract > $250K AND not small-business-set-aside → :deny)
  • (if sole-source AND no justification-documented → :deny, produce-justification)

ACL2 verifies the rule set for internal consistency. Screamer checks against existing compliance facts. The human reviews the bootstrap output and approves or corrects individual rules.

The key distinction: the LLM is not extracting knowledge from prose — it is translating a known rule system into a formal representation. The result is not "the LLM's best guess" but "the rule set as stated in the source document, mechanically transcribed."

For codified domains, the encoding cost drops from weeks to hours. The only bottleneck is human review of the 5% ambiguous rules.

See also: Sufficiency flip, Cost structure, Domain gate packages