---
OA_place: repository
OA_type: green
_id: '21092'
abstract:
- lang: eng
  text: Formal verification provides assurances that a probabilistic system satisfies
    its specification—conditioned on the system model being aligned with reality.
    We propose alignment monitoring to watch that this assumption is justified. We
    consider a probabilistic model well aligned if it accurately predicts the behaviour
    of an uncertain system in advance. An alignment score measures this by quantifying
    the similarity between the model’s predicted and the system’s (unknown) actual
    distributions. An alignment monitor observes the system at runtime; at each point
    in time it uses the current state and the model to predict the next state. After
    the next state is observed, the monitor updates the verdict, which is a high-probability
    interval estimate for the true alignment score. We utilize tools from sequential
    forecasting to construct our alignment monitors. Besides a monitor for measuring
    the expected alignment score, we introduce a differential alignment monitor, designed
    for comparing two models, and a weighted alignment monitor, which permits task-specific
    alignment monitoring. We evaluate our monitors experimentally on the PRISM benchmark
    suite. They are fast, memory-efficient, and detect misalignment early.
acknowledgement: 'This work is supported by the European Research Council under Grant
  No.: ERC-2020-AdG 101020093.'
alternative_title:
- LNCS
article_processing_charge: No
arxiv: 1
author:
- first_name: Thomas A
  full_name: Henzinger, Thomas A
  id: 40876CD8-F248-11E8-B48F-1D18A9856A87
  last_name: Henzinger
  orcid: 0000-0002-2985-7724
- first_name: Konstantin
  full_name: Kueffner, Konstantin
  id: 8121a2d0-dc85-11ea-9058-af578f3b4515
  last_name: Kueffner
  orcid: 0000-0001-8974-2542
- first_name: Vasu
  full_name: Singh, Vasu
  id: 4DAE2708-F248-11E8-B48F-1D18A9856A87
  last_name: Singh
- first_name: I
  full_name: Sun, I
  last_name: Sun
citation:
  ama: 'Henzinger TA, Kueffner K, Singh V, Sun I. Alignment monitoring. In: <i>25th
    International Conference on Runtime Verification</i>. Vol 16087. Springer Nature;
    2025:140-159. doi:<a href="https://doi.org/10.1007/978-3-032-05435-7_9">10.1007/978-3-032-05435-7_9</a>'
  apa: 'Henzinger, T. A., Kueffner, K., Singh, V., &#38; Sun, I. (2025). Alignment
    monitoring. In <i>25th International Conference on Runtime Verification</i> (Vol.
    16087, pp. 140–159). Graz, Austria: Springer Nature. <a href="https://doi.org/10.1007/978-3-032-05435-7_9">https://doi.org/10.1007/978-3-032-05435-7_9</a>'
  chicago: Henzinger, Thomas A, Konstantin Kueffner, Vasu Singh, and I Sun. “Alignment
    Monitoring.” In <i>25th International Conference on Runtime Verification</i>,
    16087:140–59. Springer Nature, 2025. <a href="https://doi.org/10.1007/978-3-032-05435-7_9">https://doi.org/10.1007/978-3-032-05435-7_9</a>.
  ieee: T. A. Henzinger, K. Kueffner, V. Singh, and I. Sun, “Alignment monitoring,”
    in <i>25th International Conference on Runtime Verification</i>, Graz, Austria,
    2025, vol. 16087, pp. 140–159.
  ista: 'Henzinger TA, Kueffner K, Singh V, Sun I. 2025. Alignment monitoring. 25th
    International Conference on Runtime Verification. RV: Runtime Verification, LNCS,
    vol. 16087, 140–159.'
  mla: Henzinger, Thomas A., et al. “Alignment Monitoring.” <i>25th International
    Conference on Runtime Verification</i>, vol. 16087, Springer Nature, 2025, pp.
    140–59, doi:<a href="https://doi.org/10.1007/978-3-032-05435-7_9">10.1007/978-3-032-05435-7_9</a>.
  short: T.A. Henzinger, K. Kueffner, V. Singh, I. Sun, in:, 25th International Conference
    on Runtime Verification, Springer Nature, 2025, pp. 140–159.
conference:
  end_date: 2025-09-19
  location: Graz, Austria
  name: 'RV: Runtime Verification'
  start_date: 2025-09-15
corr_author: '1'
date_created: 2026-01-29T16:03:43Z
date_published: 2025-09-13T00:00:00Z
date_updated: 2026-02-16T11:56:38Z
day: '13'
department:
- _id: ToHe
doi: 10.1007/978-3-032-05435-7_9
ec_funded: 1
external_id:
  arxiv:
  - '2508.00021'
fulldoi: https://doi.org/10.1007/978-3-032-05435-7_9
intvolume: '     16087'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://doi.org/10.48550/arXiv.2508.00021
month: '09'
oa: 1
oa_version: Preprint
page: 140-159
project:
- _id: 62781420-2b32-11ec-9570-8d9b63373d4d
  call_identifier: H2020
  grant_number: '101020093'
  name: Vigilant Algorithmic Monitoring of Software
publication: 25th International Conference on Runtime Verification
publication_identifier:
  eisbn:
  - '9783032054357'
  eissn:
  - 1611-3349
  issn:
  - 0302-9743
publication_status: published
publisher: Springer Nature
quality_controlled: '1'
status: public
title: Alignment monitoring
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 16087
year: '2025'
...