Metraipolis › archive › dc_91078eb476a4

Grounding Predictive Reliability through Masked Observability — arXiv:2610.39728

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.39728
License (as archived): CC0-1.0
Archived: 2026-11-01T02:25:12.710Z
SHA-256 of the archived text: 42c7b3532a65a7471e12834553295826e06ed2b1e186faf961e83656ee0db436
Stable URL of this page: https://metraipolis.com/documento/dc_91078eb476a4

How to cite

Grounding Predictive Reliability through Masked Observability — arXiv:2610.39728 — arXiv (en), https://arxiv.org/abs/2610.39728 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_91078eb476a4 (Metraipolis archive dc_91078eb476a4, sha256 42c7b3532a65a7471e12834553295826e06ed2b1e186faf961e83656ee0db436)

BibTeX

@misc{dc91078eb476a4,
  title = {Grounding Predictive Reliability through Masked Observability — arXiv:2610.39728},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39728},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_91078eb476a4; sha256 42c7b3532a65a7471e12834553295826e06ed2b1e186faf961e83656ee0db436},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39728. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

An uncertainty estimate is meaningful only if its semantics can be tied to observable predictive behavior. Normal-Inverse-Gamma (NIG) evidential regression provides a structured decomposition of predictive variability into data-scale and predictive-mean components, but marginal likelihood does not identify their allocation. We address this semantic ambiguity in masked representation learning. MORSE (Masked Observability for Reliable Structured Encoding) predicts the same hidden target under controlled changes in visible context and uses normalized cross-context variation to ground predictive-mean uncertainty, while a Gaussian objective learns the conditional mean and data scale. The normalized variation plays the role of the NIG factor $1/\nu$, which the marginal leaves unidentified; this yields a policy-relative observability variance that measures dependence on visible evidence, distinct from variation induced by resampling the training set. On a Gaussian-process benchmark with a contextual reference built from analytic Bayes conditional means, MORSE has the lowest log-variance error among compared evidential, ensemble, and dropout estimators in all nine tested settings, while the estimator closest to training-set variation perturbs the model rather than its context in every setting, so the two references separate the estimators empirically. MORSE amortizes observability estimation into one forward pass per observation state. On a heteroscedastic pulse benchmark, its predictor's cross-context variance approaches a large-sample reference as training data increase. MORSE also improves low-label transfer on PTB-XL and in-distribution trajectory prediction on IMPTC.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.39728 — 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 2026-11-01T02:12:44.180Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).