Metraipolis › archive › dc_97a57ee02a68

Certified Task-Conditioned Active Observability — arXiv:2609.28520

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.28520
License (as archived)
CC0-1.0
Archived
2026-10-08T04:26:44.668Z
SHA-256 of the archived text
b03cb9b57f2d3b3e836c443cf36855fc3753235db8c967dadb116a84c15a7346
Stable URL of this page
https://metraipolis.com/documento/dc_97a57ee02a68

How to cite

Certified Task-Conditioned Active Observability — arXiv:2609.28520 — arXiv (en), https://arxiv.org/abs/2609.28520 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_97a57ee02a68 (Metraipolis archive dc_97a57ee02a68, sha256 b03cb9b57f2d3b3e836c443cf36855fc3753235db8c967dadb116a84c15a7346)
BibTeX
@misc{dc97a57ee02a68,
  title = {Certified Task-Conditioned Active Observability — arXiv:2609.28520},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.28520},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_97a57ee02a68; sha256 b03cb9b57f2d3b3e836c443cf36855fc3753235db8c967dadb116a84c15a7346},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28520. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Before acting upon an unobservable physical system, an autonomous agent must determine which latent distinctions govern downstream tasks, how many active interventions are necessary to certify them, and when to abstain to prevent catastrophic errors. Classical observability treats state reconstruction as an unconditioned binary predicate, failing when passive observations cannot break latent degeneracies without perturbation, full microscopic inversion is prohibitively costly, and distinguishing task-irrelevant degrees of freedom wastes interaction budgets. We formalize task-conditioned active observability complexity: the minimum worst-case expected interaction cost required to identify task-relevant states under certified error and safe abstention guarantees. We prove that task-predictive equivalence induces the unique minimal sufficient quotient $\mathcal{H}/\!\sim_\tau$, leaving active observability complexity strictly invariant while eliminating superfluous distinctions. In deterministic regimes, this complexity is characterized by an optimal adaptive distinguishing tree and Bellman recursion; in noisy regimes, it obeys a stopped-transcript relative-entropy lower bound and adaptive martingale certificates that compose without independence assumptions. We instantiate a prospective certified observer with staged recovery: a nominal verifier defers candidate compilation, triggering active probing only upon evidence, while a history-measurable score shell prunes hypotheses without sacrificing risk bounds. Stress audits across high-dimensional physical systems and thousands of operational trials demonstrate certified state recovery with zero false acceptances and substantial reductions in sensor reads and model steps.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI).
Categorie arXiv: Machine Learning (stat.ML) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.28520 — 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 2026-10-08T03:50:57.909Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).