Metraipolis › archive › dc_d0ad2b9dfaca

Available Guardrails: Certifying Selective Prediction across ML Systems — arXiv:2609.22048

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.22048
License (as archived)
CC0-1.0
Archived
2026-10-10T01:45:22.788Z
SHA-256 of the archived text
4ac5b00bac7ea0483fab498f0422efab0b6cc3fbe3e652a95d02e22233d792b2
Stable URL of this page
https://metraipolis.com/documento/dc_d0ad2b9dfaca

How to cite

Available Guardrails: Certifying Selective Prediction across ML Systems — arXiv:2609.22048 — arXiv (en), https://arxiv.org/abs/2609.22048 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d0ad2b9dfaca (Metraipolis archive dc_d0ad2b9dfaca, sha256 4ac5b00bac7ea0483fab498f0422efab0b6cc3fbe3e652a95d02e22233d792b2)
BibTeX
@misc{dcd0ad2b9dfaca,
  title = {Available Guardrails: Certifying Selective Prediction across ML Systems — arXiv:2609.22048},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.22048},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d0ad2b9dfaca; sha256 4ac5b00bac7ea0483fab498f0422efab0b6cc3fbe3e652a95d02e22233d792b2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22048. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A selective predictor acts as a safety gate: it returns an output only when the prediction appears sufficiently trustworthy. Deployments increasingly require this reliability to be certified at a target precision for every reporting unit of interest, such as a tool, policy label, or patient subgroup. The main difficulty is often not whether a granted certificate is valid, but whether finite calibration data can produce one at all. As the gate becomes safer or more fine-grained, some units may receive too little evidence to certify. We make this notion of availability computable through classical exact-binomial inversion and formulate reporting-partition selection, under a fixed group order, as a dynamic program that exposes the trade-off among safety, granularity, and served traffic. The resulting frontier reveals a large population opportunity that finite-sample estimation nearly erases: a truth-informed planner gains $0.157$ mean coverage over support balancing, whereas a naive estimator recovers only $0.005$, making recovery from finite data the central challenge. Constructing candidate partitions on one planning split and selecting among them on another recovers part of this gap, improving mean coverage over support balancing by $0.060$, with the direction reproduced in $59$ of $60$ model effects across three intent-routing datasets and two architectures. A complementary validity-preserving lever, reallocating the familywise error budget across reporting units, recovers additional coverage both with population quantities and noisy estimates. The same frontier recurs, with predictor-specific ceilings, across LLM tool-calling, content moderation, lesion classification, and recommendation. Certified availability is therefore a plannable deployment resource that determines when a safety gate can be certified, at what granularity, and over how much traffic.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.22048 — 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 2026-10-10T01:14:16.671Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).