Metraipolis › archive › dc_451e324a30c8
From Concepts to Actual Causes: Toward Closing the Concept-Malfunction Gap in Robot Foundation Models — arXiv:2611.00155
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00155
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:34:03.376Z
- SHA-256 of the archived text
378d61dd6dc4b972a640db6ef439cd7499794354b4d24118dd57081330d08b85- Stable URL of this page
https://metraipolis.com/documento/dc_451e324a30c8
How to cite
From Concepts to Actual Causes: Toward Closing the Concept-Malfunction Gap in Robot Foundation Models — arXiv:2611.00155 — arXiv (en), https://arxiv.org/abs/2611.00155 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_451e324a30c8 (Metraipolis archive dc_451e324a30c8, sha256 378d61dd6dc4b972a640db6ef439cd7499794354b4d24118dd57081330d08b85)
BibTeX
@misc{dc451e324a30c8,
title = {From Concepts to Actual Causes: Toward Closing the Concept-Malfunction Gap in Robot Foundation Models — arXiv:2611.00155},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00155},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_451e324a30c8; sha256 378d61dd6dc4b972a640db6ef439cd7499794354b4d24118dd57081330d08b85},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00155. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Post-incident analysis of a robot foundation model poses a singular causal question: which internal components caused this failure, and to what degree? Mechanistic interpretability (MI), however, establishes general causal claims by decoding the concepts a policy has learned, yet knowing which concepts are encoded is insufficient for identifying the actual cause of a specific incident. In this position paper, we analyze this concept-malfunction gap by posing fault isolation in the framework of actual causality. Specifically, we formalize a fault-isolation query as a tuple of intervened internal components, counterfactual values, contingencies, and read-outs, and lay out conditions for it to be well-specified. Through this lens, we identify shortcomings of current MI approaches: they assume fixed contingencies and read out only immediate effects, letting backups obscure actual causes. We demonstrate on a toy example that these shortcomings can lead to conflicting verdicts. Lastly, based on the well-specification conditions, we outline four open research tasks toward closing the gap. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.00155 — 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 2026-11-03T10:29:48.674Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).