Metraipolis › archive › dc_e606ed4dc815

Revelation Control — arXiv:2608.23860

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.23860
License (as archived)
CC0-1.0
Archived
2026-10-18T06:35:38.805Z
SHA-256 of the archived text
ec5c791f0c834c7ff1bceb554368b4b936430eca5aa7e72eecea53274c017001
Stable URL of this page
https://metraipolis.com/documento/dc_e606ed4dc815

How to cite

Revelation Control — arXiv:2608.23860 — arXiv (en), https://arxiv.org/abs/2608.23860 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e606ed4dc815 (Metraipolis archive dc_e606ed4dc815, sha256 ec5c791f0c834c7ff1bceb554368b4b936430eca5aa7e72eecea53274c017001)
BibTeX
@misc{dce606ed4dc815,
  title = {Revelation Control — arXiv:2608.23860},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.23860},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e606ed4dc815; sha256 ec5c791f0c834c7ff1bceb554368b4b936430eca5aa7e72eecea53274c017001},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.23860. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Revelation Control is the problem of choosing priced interventions that reveal hidden state only insofar as the revealed distinctions can change a consequential decision, while accounting separately for any useful progress created by the intervention itself. We develop this theory for learning systems, where states equivalent under declared current information can respond differently to future training and favor different actions. The framework defines decision-sufficient revelation and revelation depth, separates pure information value from productive reuse, embeds static Bayes refinement into state-dependent continuation value, and gives an exact cost-adjusted factorization criterion: an additional shallow coordinate is decision-nonredundant only when states sharing a scalar summary lie on opposite sides of the priced Stop/Continue boundary. We also give a target-independent protocol for model-specific instantiation and prove that bounded stop-flip risk alone cannot certify positive expected utility under unrestricted severity. Across Qwen2.5-7B and Mistral-7B-v0.3, deeper future-learning probes have positive decision value and productive reuse yields strict equal-compute utility advantages. Qwen additionally provides evidence for a decision-nonredundant shallow revealability regime; in Mistral, a scalar continuation architecture fit only on an independent development panel retains positive familywise-adjusted lower bounds on a disjoint target panel, consistent with scalar decision sufficiency within the tested architecture family and resolution. The evidence supports structural rather than numerical transfer: the decision theory, cost accounting, continuation logic, and evaluation protocol transport, while empirical proxies, coefficients, thresholds, and even the required shallow state dimension may be system-specific.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2608.23860 — 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 2026-10-18T06:28:52.196Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).