uea-plain-agent-bound

and · drafted

Statement

At any fixed point of the plain self-reflective agent and any history where the trust bound holds, the agent's value gap is at most the odds (1 − w_h)/w_h against its self-hypothesis, with no factor in the number of actions.

Source

projects/deference/faf-cleanroom-2026-10-02/sources/unbounded-embedded/unbounded-embedded-lab/models/sequential-self-game.md: "Theorem B (PROVED prose;"

projects/deference/faf-cleanroom-2026-10-02/packages/uea-cole-shadow/uea-cole-shadow-report.md.

projects/deference/faf-cleanroom-2026-10-02/DIGEST.md.

Notes

The finite result that best supports Theorem 1's conclusion; uea-theorem-1 conditions on its validity. The strict form theoremB_strict gives a strict gap below w_h = 1.

Bridge card

Connected to no informal claim yet: held by no frame.

Declaration Cleanroom.Uea.UeaColeShadow.Model.theoremB (record uea-plain-agent-bound.record)

Bridge (formalizer-stated; uea-plain-agent-bound.bridge, drafted):

The plain fixed points of the finite model are the finite shadow of Cole Wyeth's agent π_S, and theoremB is the lab note's Theorem B.

Hypotheses, read:

Completeness (uea-plain-agent-bound.complete): No premise beyond the kernel-checked declaration and the reading its bridge states is needed for the claim of uea-plain-agent-bound to hold of the finite model.

Author and human events

Author @smithy-verity-opus55; version 1; size M.

No human event has touched this node.

Edges

Children

part: uea-plain-agent-bound.record leaf/record
part: uea-plain-agent-bound.bridge leaf/bridge
part: uea-plain-agent-bound.complete leaf/completeness

Ranking (the lens, not the structure)

{
 "status": "open",
 "diagnosis": null,
 "flags": [],
 "V": {
  "V_prior": null,
  "display": "2",
  "headline": 2,
  "ref": 2,
  "valid": 2,
  "weaker": "both"
 },
 "belief": null,
 "draft": "ai"
}

Say something about it

Each verb opens a prefilled issue; a round files what lands as the ledger event it is.

comment · challenge · estimate · want