Metraipolis › archive › dc_c44aa685779e

Dynamical Parameters: An Interpretability Framework for Time-Series Foundation Models — arXiv:2609.34316

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34316
License (as archived)
CC0-1.0
Archived
2026-10-07T20:57:39.190Z
SHA-256 of the archived text
dd256b92507ae7abd429f58556731bc26fe9b4c0c5c8c8a26f160372045a71ba
Stable URL of this page
https://metraipolis.com/documento/dc_c44aa685779e

How to cite

Dynamical Parameters: An Interpretability Framework for Time-Series Foundation Models — arXiv:2609.34316 — arXiv (en), https://arxiv.org/abs/2609.34316 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c44aa685779e (Metraipolis archive dc_c44aa685779e, sha256 dd256b92507ae7abd429f58556731bc26fe9b4c0c5c8c8a26f160372045a71ba)
BibTeX
@misc{dcc44aa685779e,
  title = {Dynamical Parameters: An Interpretability Framework for Time-Series Foundation Models — arXiv:2609.34316},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34316},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c44aa685779e; sha256 dd256b92507ae7abd429f58556731bc26fe9b4c0c5c8c8a26f160372045a71ba},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34316. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This work studies a central gap in interpreting time-series foundation models (TSFMs): a dynamical property may be accessible in a hidden state even when the forecast fails to respond correctly as that property changes. We formalize these properties as Dynamical Parameters, including trend slope, oscillation frequency, and autoregressive dependence. We compare their representation accessibility, measured by recovery from hidden states, with their forecast response, measured by agreement with the expected forecast change. Across nine frozen TSFMs and thirteen laws, 42 of 63 model-parameter cells achieve accessibility above 0.95, whereas their median reference-aligned response relative to the conditional reference is only 0.46. To explain this gap, causal geometry compares the hidden-state change required to produce the reference response with the change induced by the parameter intervention. Directly modifying the hidden state recovers the reference response, but the parameter intervention often moves the state in a different direction. These results show that accessible parameter information need not be expressed in forecasts when input changes miss the required hidden-state direction.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.34316 — 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 2026-10-07T20:29:01.511Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).