Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-10T15:18:34.711294Z
Paper Citation Record · LEDGER
Robust Optimization for Mitigating Reward Hacking with Correlated Proxies
As of 5 August 2026, this Paper Citation Record lists 6 of 6 outbound references and 1 inbound Pith citation observation for arXiv:2604.12086.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-07-13T02:39:02.891861Z
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
6 of 6 outbound references displayed
- verified exact0
- verified fuzzy2
- unresolved2
- parse uncertain0
- malformed identifier1
- metadata mismatch1
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation fdd513df-48e8-4f25-a680-877992d8f2a5 · outbound
This paper cites Oliphant, Matt Haberland, Tyler Reddy, David Cournapeau, Evgeni Burovski, Pearu Peterson, Warren Weckesser, Jonathan Bright, St´ efan J.
Robust Optimization for Mitigating Reward Hacking with Correlated Proxies Oliphant, Matt Haberland, Tyler Reddy, David Cournapeau, Evgeni Burovski, Pearu Peterson, Warren Weckesser, Jonathan Bright, St´ efan J
Reference 1
- Resolution
- metadata mismatch
- doi, observed 2026-05-10T15:20:31.842146Z
Source-reported events for the cited work
correction dated 2020-03-04. Source: crossref record 10.1038/s41592-020-0772-5->10.1038/s41592-019-0686-2:correction, observed 2026-07-11T03:08:19.430942+00:00. This notice travels one citation hop only.
Observation c3352753-1e46-4853-890c-230e5969ff7b · outbound
This paper cites (L(s, a)−λ 1 Rproxy(s,a) V −λ 2)2 4λ3 # +λ1r+λ 2M+λ 3(M2+V 2) (20) We now compute the gradients of the dual objective with respect to the dual variables: ∂l0 ∂λ1 =−E µπref.
Robust Optimization for Mitigating Reward Hacking with Correlated Proxies (L(s, a)−λ 1 Rproxy(s,a) V −λ 2)2 4λ3 # +λ1r+λ 2M+λ 3(M2+V 2) (20) We now compute the gradients of the dual objective with respect to the dual variables: ∂l0 ∂λ1 =−E µπref
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T04:10:52.502911Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation cee8c42a-ff87-43a6-b19c-3846beea47eb · outbound
This paper cites an unresolved cited work.
Robust Optimization for Mitigating Reward Hacking with Correlated Proxies Unresolved cited work
Reference 3
- Resolution
- unresolved
- raw_fallback, observed 2026-05-18T04:10:52.509742Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation aaa2ac24-6f0d-4bde-9509-a79ae1f116e8 · outbound
This paper cites an unresolved cited work.
Robust Optimization for Mitigating Reward Hacking with Correlated Proxies Unresolved cited work
Reference 4
- Resolution
- unresolved
- raw_fallback, observed 2026-05-18T04:10:52.514685Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation e3ea21a6-7d97-4e3c-94e0-9f65899211db · outbound
This paper cites sprinkler state.
Robust Optimization for Mitigating Reward Hacking with Correlated Proxies sprinkler state
Reference 5
- Resolution
- malformed identifier
- raw_fallback, observed 2026-05-18T04:10:52.507192Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation bb76546b-be2e-421e-bb52-ceccf55e2813 · outbound
This paper cites We should note that the reason these frameworks are potentially applicable is that our formulation admits a closed-form solution for the inner minimization.
Robust Optimization for Mitigating Reward Hacking with Correlated Proxies We should note that the reason these frameworks are potentially applicable is that our formulation admits a closed-form solution for the inner minimization
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T04:10:52.512398Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Pith citing papers
Observation e5325547-b6a6-435c-a3ef-e33544c56a13 · inbound
Multimodal Reward Hacking in Reinforcement Learning cites this paper.
Multimodal Reward Hacking in Reinforcement Learning Robust Optimization for Mitigating Reward Hacking with Correlated Proxies
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-07-13T02:39:02.891861Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.