Metraipolis › archive › dc_69abaaaffc30

Pricing the Risk of Runtime Compression: Anytime-Valid Admission and a Served-Output Law for Compressed Serving State — arXiv:2608.15810

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.15810
License (as archived): CC0-1.0
Archived: 2026-10-18T17:41:05.659Z
SHA-256 of the archived text: 2b4c3a73fce98f9bd1ae24c578d547afa1ead83af2cca5dacc9ef3beb62dd09c
Stable URL of this page: https://metraipolis.com/documento/dc_69abaaaffc30

How to cite

Pricing the Risk of Runtime Compression: Anytime-Valid Admission and a Served-Output Law for Compressed Serving State — arXiv:2608.15810 — arXiv (en), https://arxiv.org/abs/2608.15810 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_69abaaaffc30 (Metraipolis archive dc_69abaaaffc30, sha256 2b4c3a73fce98f9bd1ae24c578d547afa1ead83af2cca5dacc9ef3beb62dd09c)

BibTeX

@misc{dc69abaaaffc30,
  title = {Pricing the Risk of Runtime Compression: Anytime-Valid Admission and a Served-Output Law for Compressed Serving State — arXiv:2608.15810},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15810},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_69abaaaffc30; sha256 2b4c3a73fce98f9bd1ae24c578d547afa1ead83af2cca5dacc9ef3beb62dd09c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15810. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Runtime compression of serving state trades quality for capacity with no priced guarantee: systems adapt precision on load signals with no soundness statement, and certified approaches budget request-level risk by a union bound over a pre-declared event count. We show the union budget exhausts on every long request in a production serving stack (100% of requests), and replace it with an anytime-valid, physically accounted ledger whose bound holds at every one of 352,333 admission calls on live traffic and which, in a pre-registered held-out confirmatory round, halves the exact-fallback rate at matched risk (0.30 -> 0.14) -- coverage is bought at a price the account states. We then price the remaining distance from the certified witness to what a user experiences: a machine-checked design law (TV <= tanh(a_q w_thr)) turns the served-TV target into a threshold knob, and a three-layer audit of its instantiation -- an operator-norm query envelope measured 1.5x from tight, a measured-ellipsoid replacement for the Cauchy-Schwarz ball that buys nothing (0.89x, held-out sound), and the gate's operating point (~700x) -- localizes the entire 1064x gap to the operating point, a price the law now states rather than an unknown. A priced bound is worth nothing on a request one has not seen, so the third link is the quantifier: exchangeable extrapolation across 80 serving histories replaces binary conformal prediction's vacuous certificates with order-statistic bounds that discriminate (0.41 against 0.51 calibration risk). All probabilistic kernels are Lean 4-checked (228 exported theorems, no sorry); which object deserves this machinery at all is settled empirically in a companion paper that adjudicates -- and rejects -- the natural alternative of certifying routing. What ships is an account: risk you can spend, a gap you can read off a law, and a bound that survives the request you have not seen.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.15810 — 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 2026-10-18T16:29:13.831Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).