Metraipolis › archive › dc_bc9594476e08
Audit Before You Commit: Locating Belief Failures in Active Identification for One-Shot Manipulation — arXiv:2609.30608
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30608
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T03:14:47.306Z
- SHA-256 of the archived text
ae2b4219e8379db2cf10b6dcb3c199d8013fcee6464c8077ca8260725ef7a440- Stable URL of this page
https://metraipolis.com/documento/dc_bc9594476e08
How to cite
Audit Before You Commit: Locating Belief Failures in Active Identification for One-Shot Manipulation — arXiv:2609.30608 — arXiv (en), https://arxiv.org/abs/2609.30608 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc9594476e08 (Metraipolis archive dc_bc9594476e08, sha256 ae2b4219e8379db2cf10b6dcb3c199d8013fcee6464c8077ca8260725ef7a440)
BibTeX
@misc{dcbc9594476e08,
title = {Audit Before You Commit: Locating Belief Failures in Active Identification for One-Shot Manipulation — arXiv:2609.30608},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30608},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc9594476e08; sha256 ae2b4219e8379db2cf10b6dcb3c199d8013fcee6464c8077ca8260725ef7a440},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30608. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
A robot that probes a few times before one irreversible action, such as tapping a surface before inserting a peg, must decide when the evidence is enough to commit. We argue that this decision rests on two conditions that existing methods do not separate: the belief must still cover the truth in the coordinate that decides the action, and the failure model that scores actions must track realized failure. We audit both conditions separately, offline and with ground truth, on a deployed probe-then-commit pipeline: a particle belief, a scenario failure score, and one commit. On simulated insertion, more taps sharpen the belief while the truth leaves its support on 16.9% of episodes and the failure score turns optimistic by 0.31. Conformal calibration restores coverage but not the decision: confidently wrong instances still pass a confidence gate. The audit's signatures instead point at the observation model, where a hand scan finds a 2.1 mm error in the tap boundary. Correcting that one number cuts failure from 0.354 to 0.112 on untouched instances and transfers unrefitted to a second engine, while in a third engine the same audit suggests an execution-model mismatch instead. Across seven task families in three engines, a few probes at a fixed executor reduce miss or failure. On a physical arm inserting a tool into a rigid pocket by touch, the gain and the audit's two conditions reproduce, and replaying the recorded taps under an injected model error shows the audit's signature on real data. Additional materials are available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-28 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.30608 — 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 2026-10-08T02:58:08.821Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).