Metraipolis › archive › dc_4dff496f9926
Interpolation Is Not Invariance: Pair Count Is Not Coverage in Transformation Audits — arXiv:2609.14870
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.14870
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T22:53:25.698Z
- SHA-256 of the archived text
e6866754e1bb010c014d936c3d16c05f67365705101c70d6b23105db3ccf3b68- Stable URL of this page
https://metraipolis.com/documento/dc_4dff496f9926
How to cite
Interpolation Is Not Invariance: Pair Count Is Not Coverage in Transformation Audits — arXiv:2609.14870 — arXiv (en), https://arxiv.org/abs/2609.14870 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4dff496f9926 (Metraipolis archive dc_4dff496f9926, sha256 e6866754e1bb010c014d936c3d16c05f67365705101c70d6b23105db3ccf3b68)
BibTeX
@misc{dc4dff496f9926,
title = {Interpolation Is Not Invariance: Pair Count Is Not Coverage in Transformation Audits — arXiv:2609.14870},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.14870},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4dff496f9926; sha256 e6866754e1bb010c014d936c3d16c05f67365705101c70d6b23105db3ccf3b68},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14870. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Counting equivalent pairs is a common way to report transformation-audit coverage, but it can substantially overstate the constraints imposed by an audit: pairs generated from the same semantic object are correlated, and complete orbit graphs contain algebraically redundant edges. We therefore distinguish four complementary quantities---edge count $m$, effective contrast rank $s$, population support rank $r$, and graph spectral gap $\eta$---and characterize their roles in audit coverage and deployment reliability. Under a rank-$r$ Gaussian contrast model, a population-invariant calibrated reader exists exactly when the anchor has a component in $\ker T$. When an audit has rank $s < r$, its unobserved risk is $R^\star/U$, with $U \sim \operatorname{Beta}((r-s)/2,s/2)$; when $s \ge r$, exact calibrated interpolation is infeasible. The same distinction appears in orbit topology: a spanning tree imposes the same exact-null constraints as a complete graph, while a sharp graph Poincare inequality propagates edge-level drift to an entire orbit at a cost proportional to $1/\eta$. Cyclic audits can additionally yield zero pair-level leave-one-out error without holding out any semantic object. To address these failures, we derive exact block-Woodbury leave-one-orbit-out updates and introduce a source-disjoint deployment gate over finitely many candidate readers. The gate retains the original reader unless uncertainty bounds certify lower drift within a prescribed clean-utility budget. etc..
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.14870 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T22:29:03.748Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).