{"corr_author":"1","ec_funded":1,"author":[{"id":"40876CD8-F248-11E8-B48F-1D18A9856A87","last_name":"Henzinger","full_name":"Henzinger, Thomas A","orcid":"0000-0002-2985-7724","first_name":"Thomas A"},{"last_name":"Kueffner","id":"8121a2d0-dc85-11ea-9058-af578f3b4515","first_name":"Konstantin","full_name":"Kueffner, Konstantin","orcid":"0000-0001-8974-2542"},{"id":"4DAE2708-F248-11E8-B48F-1D18A9856A87","last_name":"Singh","first_name":"Vasu","full_name":"Singh, Vasu"},{"first_name":"I","full_name":"Sun, I","last_name":"Sun"}],"quality_controlled":"1","oa_version":"Preprint","article_processing_charge":"No","month":"09","external_id":{"arxiv":["2508.00021"]},"title":"Alignment monitoring","date_published":"2025-09-13T00:00:00Z","abstract":[{"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.","lang":"eng"}],"citation":{"mla":"Henzinger, Thomas A., et al. “Alignment Monitoring.” 25th International Conference on Runtime Verification, vol. 16087, Springer Nature, 2025, pp. 140–59, doi:10.1007/978-3-032-05435-7_9.","ama":"Henzinger TA, Kueffner K, Singh V, Sun I. Alignment monitoring. In: 25th International Conference on Runtime Verification. Vol 16087. Springer Nature; 2025:140-159. doi:10.1007/978-3-032-05435-7_9","ieee":"T. A. Henzinger, K. Kueffner, V. Singh, and I. Sun, “Alignment monitoring,” in 25th International Conference on Runtime Verification, Graz, Austria, 2025, vol. 16087, pp. 140–159.","short":"T.A. Henzinger, K. Kueffner, V. Singh, I. Sun, in:, 25th International Conference on Runtime Verification, Springer Nature, 2025, pp. 140–159.","apa":"Henzinger, T. A., Kueffner, K., Singh, V., & Sun, I. (2025). Alignment monitoring. In 25th International Conference on Runtime Verification (Vol. 16087, pp. 140–159). Graz, Austria: Springer Nature. https://doi.org/10.1007/978-3-032-05435-7_9","chicago":"Henzinger, Thomas A, Konstantin Kueffner, Vasu Singh, and I Sun. “Alignment Monitoring.” In 25th International Conference on Runtime Verification, 16087:140–59. Springer Nature, 2025. https://doi.org/10.1007/978-3-032-05435-7_9.","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."},"publication_status":"published","OA_type":"green","publication_identifier":{"issn":["0302-9743"],"eisbn":["9783032054357"],"eissn":["1611-3349"]},"year":"2025","page":"140-159","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","language":[{"iso":"eng"}],"acknowledgement":"This work is supported by the European Research Council under Grant No.: ERC-2020-AdG 101020093.","doi":"10.1007/978-3-032-05435-7_9","publication":"25th International Conference on Runtime Verification","date_created":"2026-01-29T16:03:43Z","_id":"21092","publisher":"Springer Nature","main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2508.00021"}],"status":"public","date_updated":"2026-02-16T11:56:38Z","project":[{"grant_number":"101020093","_id":"62781420-2b32-11ec-9570-8d9b63373d4d","name":"Vigilant Algorithmic Monitoring of Software","call_identifier":"H2020"}],"volume":16087,"day":"13","arxiv":1,"OA_place":"repository","conference":{"location":"Graz, Austria","name":"RV: Runtime Verification","end_date":"2025-09-19","start_date":"2025-09-15"},"oa":1,"alternative_title":["LNCS"],"intvolume":" 16087","type":"conference","department":[{"_id":"ToHe"}]}