Metraipolis › archive › dc_d6eccce27c65

RAEGL: Risk-Aware Evidence-Gated Learning for Selective Contextual Routing under Temporal Shift — arXiv:2609.33340

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33340
License (as archived)
CC0-1.0
Archived
2026-10-07T22:37:23.409Z
SHA-256 of the archived text
65563115432762d9b267e504159a9d7e4e85c976d6b83e73dd283aefce61d243
Stable URL of this page
https://metraipolis.com/documento/dc_d6eccce27c65

How to cite

RAEGL: Risk-Aware Evidence-Gated Learning for Selective Contextual Routing under Temporal Shift — arXiv:2609.33340 — arXiv (en), https://arxiv.org/abs/2609.33340 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d6eccce27c65 (Metraipolis archive dc_d6eccce27c65, sha256 65563115432762d9b267e504159a9d7e4e85c976d6b83e73dd283aefce61d243)
BibTeX
@misc{dcd6eccce27c65,
  title = {RAEGL: Risk-Aware Evidence-Gated Learning for Selective Contextual Routing under Temporal Shift — arXiv:2609.33340},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33340},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d6eccce27c65; sha256 65563115432762d9b267e504159a9d7e4e85c976d6b83e73dd283aefce61d243},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33340. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Contextual specialization can improve forecasting accuracy, but a correction selected on one historical interval may become unreliable under temporal distribution shift. To address this issue, we propose RAEGL, a Risk-Aware Evidence-Gated Learning framework for selective contextual forecasting. RAEGL retains a validated global predictor by default and activates a contextual residual only when pre-deployment evidence supports its use. The framework separates candidate selection from gate calibration and jointly evaluates randomization significance, practically meaningful gain, and temporal stability. Experiments on real-world audits and controlled panels show how RAEGL can prevent harmful contextual deployment while making conservative opportunity costs explicit. In a reconstructed Our World in Data audit, exact fallback avoids RMSE degradations of 0.0960 and 0.0239 caused by two validation-selected corrections. In a sealed World Development Indicators evaluation, a region-based correction passes the randomization test but is withheld because its gain is only 0.000092, its country-clustered 95% confidence interval crosses zero, and only 0.02% of bootstrap replicates reach the practical threshold. In controlled panels, the stability- and support-aware extension activates in 97.2% of strong, stable-context runs while rejecting all high-drift settings. These results support RAEGL as an auditable, evidence-based mechanism for managing contextual deployment risk and as a conservative alternative to validation-driven contextual selection.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.33340 — 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 2026-10-07T22:14:27.922Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).