AXN 0335 is the content-derived identifier of Alexanarch deposit #191. 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 paperβs argument proceeds in two levels.
Structural claim
If a filter:
- identifies high-perplexity or low-coverage language; - rejects it before inference;
then it is, by function, pruning the linguistic tail from the input path.
Coupling hypothesis
Inference and training are distinct layers, but the paper proposes that they can couple through:
- retained interaction logs; - standardized procurement patterns; - population-scale deployment; - mediated feedback into later model updates.
The paper contrasts two frames for the same properties:
- high perplexity as attack signal; - high perplexity as rare, informative tail data.
It argues that the reviewed mitigation turns model-relative distance from the training distribution into a security category.
The alternative controls proposed are:
- rate limiting; - token and output budgets; - language-aware routing; - content-neutral resource controls; - preservation of tail-language demand in logs.
0335COMPOSITIONALc14ff9d43471674482e69e63a8f7a16719e5ab9dd1fa2d36136a014b87097981AXN:0335.COMPOSITIONAL.ππ‘βπΉππͺ§ — each names this record (/api/axn-aliases.json)8f3c2c731e4dd62bff552e509be72f1edf5c5c93677b29ad9004509e3f43b282 — 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:070E.NON.π₯π³π₯ππβοΈ — model-collapse (loops; kernel[K24].source)Resolver rule: alexanarch.org/axn/<HEX> ·
term set: AXN identifier set ·
machine index: /api/axn-index.json