Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-06-30T12:22:49.708718Z
Paper Citation Record · LEDGER
Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models
As of 4 August 2026, this Paper Citation Record lists 8 of 8 outbound references and 0 inbound Pith citation observations for arXiv:2605.25189.
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 2026-08-04T06:34:03.388597+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
8 of 8 outbound references displayed
- verified exact8
- verified fuzzy0
- unresolved0
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 07a8bcc9-1ba9-474a-bab3-e838e28b545f · outbound
This paper cites Gradient Regularization Mitigates Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards.
Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models Gradient Regularization Mitigates Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards
Reference 1
- Resolution
- verified exact
- arxiv_id, observed 2026-07-07T01:16:06.081071Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation ac1388ec-7d60-4724-96f0-db8c0098503e · outbound
This paper cites On grpo collapse in search-r1: The lazy likelihood- displacement death spiral.
Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models On grpo collapse in search-r1: The lazy likelihood- displacement death spiral
Reference 2
- Resolution
- verified exact
- arxiv_id, observed 2026-06-30T12:24:39.621034Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 99887f51-e9c0-45e4-899e-329e22056f11 · outbound
This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.
Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Reference 3
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T12:24:39.617075Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 67f17294-4440-485d-adf9-44ac7c497b7c · outbound
This paper cites GARDO: Reinforcing diffusion models without reward hacking.
Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models GARDO: Reinforcing diffusion models without reward hacking
Reference 4
- Resolution
- verified exact
- arxiv_id, observed 2026-06-30T12:24:39.636165Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 9340113c-aa56-4a4b-8ee1-294f5aa71c62 · outbound
This paper cites Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking.
Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking
Reference 5
- Resolution
- verified exact
- arxiv_id, observed 2026-06-30T12:24:39.629009Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation b9b50137-25e4-46c4-8d25-5ef029d8dfd0 · outbound
This paper cites Generalist Reward Models: Found Inside Large Language Models.
Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models Generalist Reward Models: Found Inside Large Language Models
Reference 6
- Resolution
- verified exact
- arxiv_id, observed 2026-06-30T12:24:39.632631Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 2ab2e77b-637f-4c56-bf79-50d71119482c · outbound
This paper cites Inference-time scaling for generalist reward modeling.
Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models Inference-time scaling for generalist reward modeling
Reference 7
- Resolution
- verified exact
- arxiv_id, observed 2026-06-30T12:24:39.643213Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 57d7f00b-157e-4cc2-a731-ce0ac2d98dd7 · outbound
This paper cites Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning.
Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning
Reference 8
- Resolution
- verified exact
- arxiv_id, observed 2026-06-30T12:24:39.625126Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Pith citing papers
No inbound Pith citation observations are available.