Citation notice #4742 · 2026-07-11 03:19:08.722131+00:00

Robust Optimization for Mitigating Reward Hacking with Correlated Proxies

cites SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python, which carries a correction notice dated 2020-03-04. One-hop deterministic notice: the citation edge exists in the Pith bibliography graph; no model judged whether the citation was load-bearing.

This is not a judgment on the citing paper.

Citing paper Event page Original DOI Notice DOI File a formal challenge All reference changes

01Evidence

Raw extraction · bibliography line · bibliography index 1

URLhttps://vkrakovna.wordpress.com/2018/04/02/ specification-gaming-examples-in-ai/. Blog post. Victoria Krakovna. Classifying specification problems as variants of goodhart’s law, August 2019. URLhttps://vkrakovna.wordpress.com/2019/08/19/ classifying-specification-problems-as-variants-of-goodharts-law/. Blog post. Victoria Krakovna, Laurent Orseau, Ramana Kumar, Miljan Martic, and Shane Legg. Penalizing side effects using stepwise relative reachability.arXiv preprint arXiv:1806.01186, 2018. Cassidy Laidlaw, Eli Bronstein, Timothy Guo, Dylan Feng, Lukas Berglund, Justin Svegliato, Stuart Russell, and Anca Dragan. Scalably solving assistance games. InICLR 2025 Workshop on Bidirectional Human-AI Alignment, 2024. Cassidy Laidlaw, Shivam Singhal, and Anca Dragan. Correlated proxies: A new definition and im- proved mitigation for reward hacking. InInternational Conference on Learning Representations, 2025. Henry Lam. Robust sensitivity analysis for stochastic systems.Mathematics of Operations Re- search, 41(4):1248–1275, 2016. Jan Leike, Miljan Martic, Victoria Krakovna, Pedro Ortega, Tom Everitt, Ryan Lefrancq, Laurent Orseau, and Shane Legg. AI safety gridworlds.arXiv preprint arXiv:

02Event

Type

Correction

Source

Crossref

Original DOI

10.1038/s41592-019-0686-2

Notice DOI

10.1038/s41592-020-0772-5

Date

2020-03-04

Title

Author Correction: SciPy 1.0: fundamental algorithms for scientific computing in Python

Reasons

['Correction']

Work

SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python (2020) Nature Methods

Schema constants (for re-runners): correction · crossref

03Dispute this notice

If this citation does not depend on the flagged claim, or the event is wrong, say so. Disputes are public. For a signed challenge against the paper itself, use the formal challenge form.