Metraipolis › archive › dc_7b2209b3f264

What Does an Observability Foundation Model Know? — arXiv:2610.05577

Source
arXiv
Original
https://arxiv.org/abs/2610.05577
License (as archived)
CC0-1.0
Archived
2026-10-06T05:27:01.157Z
SHA-256 of the archived text
331e467d9b507eaba680e97c2e893d94758742de74b1417012b50904ac98ae7c
Stable URL of this page
https://metraipolis.com/documento/dc_7b2209b3f264

How to cite

What Does an Observability Foundation Model Know? — arXiv:2610.05577 — arXiv, https://arxiv.org/abs/2610.05577 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7b2209b3f264 (Metraipolis archive dc_7b2209b3f264, sha256 331e467d9b507eaba680e97c2e893d94758742de74b1417012b50904ac98ae7c)
BibTeX
@misc{dc7b2209b3f264,
  title = {What Does an Observability Foundation Model Know? — arXiv:2610.05577},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05577},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7b2209b3f264; sha256 331e467d9b507eaba680e97c2e893d94758742de74b1417012b50904ac98ae7c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05577. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A linear probe can show that a label is recoverable from a model's hidden states, but not whether that goes beyond what the input already reveals, or whether the model uses it. We audit Toto, an observability forecasting foundation model, on the Benchmark of Observability Metrics (BOOM) across five series-disjoint resplits, comparing linear probes on its frozen residual stream with models that read the raw input window and with Toto's architecture stripped of its trained configuration. Short-vs-medium cadence and metric type are more linearly recoverable from Toto's residuals than from the strongest raw-window model in every resplit (macro-F1 0.766 vs. 0.633 and 0.545 vs. 0.498). Domain is nearly tied, and series cardinality is recovered far better from the raw window. MOMENT-base shows related cadence, metric-type, and domain readouts. Recoverability is not use: exchanging Toto's residuals with those of high-burst donors moves a future-burstiness readout as intended but does not make forecasts consistently burstier than a randomized donor. A BOOM-trained coordination probe has negative zero-shot R^2 on the tested external benchmarks. We report each label against its strongest baseline.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.05577 — 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 2026-10-06T05:24:06.047Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).