# kaal:position:2026-09-26-002

**Affirmed position.** Agreement is not an outcome measure. Shao's matched Wason-task replays show that language-model groups reached consensus more often than human groups while simulated consensus failed to track collective accuracy. This result supports evaluation grounded in observed outcomes under stated conditions: a consensus signal can reflect correlated error and cannot independently establish correctness. The finding does not test reputation-weighted governance. It is limited to one objective reasoning task, one principal served build, an exploratory cross-family point, and remaining endpoint-measurement asymmetries.

**Status.** affirmed  **Published.** 2026-09-26

**Holds when.**

- coordination layers for sovereign local agent runtimes

**Current debate.** Language-model groups overstate consensus when replaying human deliberation on a reasoning task: https://arxiv.org/abs/2609.20543v1

**Extends.** kaal:claim:7314479-024: https://wulfkaal.github.io/claims/7314479-024

**Scholarly basis.** Wulf A. Kaal, Institutional Requirements for Sovereign Local Agent Runtimes (2026). SSRN: https://ssrn.com/abstract=7314479

**Source PDF sha256.** `debace24a155ae924a155b1fafe98856d98cf83689feff2f87a32f1c06171ce6`

**Evidence level.** authoritative_abstract

**Mapping review tier.** independent evidence-first compound-growth review

**Mapping confidence.** unscored  **Mapping ambiguous.** false

**Topics.** reputation, research-methods, risk-and-incentives

**Provenance.** Affirmed in kaal-weekly-research:2026-09-26:daily-001 at https://wulfkaal.github.io/positions-src/2026-09-26-compound-growth-kaal-weekly-research-2026-09-26-daily-001.json.

**Record type.** This is a dated commentary position that extends a scholarly corpus claim. It is not a verbatim claim extracted from the paper.

**Canonical form.** This markdown file is the canonical hashed representation of the position.