AXN 0289 is the content-derived identifier of Alexanarch deposit #737. It is an identifier, not a copy of the work: the hex marks position in the archive, and the six-glyph suffix is a display hash of the canonical text’s SHA-256, so the identifier is derived from the work rather than assigned to it.
The AI System as Closed-System Test Bed is a methods paper by Nobel Glas that translates the Semantic Deviation Principle into quantities measurable from language-model probabilities.
The first quantity compares each realized tokenโs surprisal with the modelโs expected surprisal at that position. Positive values indicate a token less expected than the modelโs baseline; negative values indicate convergence toward highly probable continuation. A second, more expensive quantity compares sampled future continuations with and without a contextual intervention.
The paper proposes experiments asking whether these measures separate literary, formulaic, and AI-generated prose; whether a deposited concept selectively changes model continuations; and whether the signal can guide training. The Crimson Hexagonal Archive corpus is treated separately to reduce self-validation.
The work is a pre-registration rather than a finding. โMeaning,โ โslop,โ and โdeviationโ remain operational terms inside the experiment, not quantities already shown to correspond to literary or human significance.
0289GOVERNANCE499f7b5c37205dbb271bfe88dd7b5a34cb0e19bbb3b9d8d7d917133f0ef82747AXN:0289.GOVERNANCE.๐๐โ๐ซถ๐๐ถ — each names this record (/api/axn-aliases.json)e640abbd698802ca75daab95fdd94fcf518e9c19a32e4703f4c04cc829197459 — unverified input not retained; derivation ledgerRead from the fields that record them (/data/axn-relations.json); a hash names bytes and supplies no relation.
AXN:0AC4.NON.โ๐๐ปโ๏ธ๐๐ — newsguard-ai-false-claim-monitor (red teaming as a remedy; kernel[K27].source)Resolver rule: alexanarch.org/axn/<HEX> ·
term set: AXN identifier set ·
machine index: /api/axn-index.json