Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-07-08T21:20:07.569587Z
Paper Citation Record · LEDGER
More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges
As of 19 August 2026, this Paper Citation Record lists 17 of 17 outbound references and 2 inbound Pith citation observations for arXiv:2607.05904.
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 2026-08-19T06:32:44.657259+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-02T05:30:04.547511Z
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
17 of 17 outbound references displayed
- verified exact6
- verified fuzzy0
- unresolved0
- parse uncertain0
- malformed identifier1
- metadata mismatch10
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 506e4a48-45dd-4232-bdb2-632c0437beae · outbound
This paper cites Constitutional AI: Harmlessness from AI Feedback.
More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges Constitutional AI: Harmlessness from AI Feedback
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-07-08T21:25:38.646181Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation a2a38675-5ead-4f4a-89e7-1e1b34693671 · outbound
This paper cites Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models.
More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
Reference 2
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-08T21:25:38.654700Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation e426a20c-f573-4c4b-a2db-4c6fccabcff7 · outbound
This paper cites Reward Model Ensembles Help Mitigate Overoptimization.
More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges Reward Model Ensembles Help Mitigate Overoptimization
Reference 3
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-08T21:25:38.636176Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 6539054c-9dac-4621-b592-f3be852adeb6 · outbound
This paper cites Scaling Laws for Reward Model Overoptimization.
More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges Scaling Laws for Reward Model Overoptimization
Reference 4
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-08T21:25:38.660138Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 5f5cc307-ba46-4aab-bcad-d2edb1acc691 · outbound
This paper cites On scalable oversight with weak LLMs judging strong LLMs.
More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges On scalable oversight with weak LLMs judging strong LLMs
Reference 5
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-08T21:25:38.643507Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 3aa99a92-a834-4240-aaea-2d299ae90004 · outbound
This paper cites When Does Verification Pay Off? A Closer Look at LLMs as Solution Verifiers.
More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges When Does Verification Pay Off? A Closer Look at LLMs as Solution Verifiers
Reference 6
- Resolution
- verified exact
- local_arxiv, observed 2026-07-08T21:25:38.633754Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 69d997df-802e-42d1-aafe-6cd36dd11edf · outbound
This paper cites Spontaneous Reward Hacking in Iterative Self-Refinement.
More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges Spontaneous Reward Hacking in Iterative Self-Refinement
Reference 7
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-08T21:25:38.621167Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation c8f2e35b-8718-4d47-a563-965679ca8cff · outbound
This paper cites Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms.
More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms
Reference 8
- Resolution
- verified exact
- local_arxiv, observed 2026-07-08T21:25:38.651895Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation bb7db7e6-05e1-4192-86a6-93676208df0a · outbound
This paper cites Towards Understanding Sycophancy in Language Models.
More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges Towards Understanding Sycophancy in Language Models
Reference 9
- Resolution
- verified exact
- local_arxiv, observed 2026-07-08T21:25:38.623673Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 74981873-42cf-49ce-8db6-a0512b782060 · outbound
This paper cites RLSR: Reinforcement Learning from Self Reward.
More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges RLSR: Reinforcement Learning from Self Reward
Reference 10
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-08T21:25:38.648851Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation fad3a143-a4bd-4dc4-9ba6-2eac61ce336e · outbound
This paper cites A Long Way to Go: Investigating Length Correlations in RLHF.
More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges A Long Way to Go: Investigating Length Correlations in RLHF
Reference 11
- Resolution
- verified exact
- local_arxiv, observed 2026-07-08T21:25:38.638530Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 8ecccce0-e3b5-4121-8e76-605d931b0bb1 · outbound
This paper cites Language Models Learn to Mislead Humans via RLHF.
More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges Language Models Learn to Mislead Humans via RLHF
Reference 12
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-08T21:25:38.626147Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 3f3cf442-54df-48bf-9996-6e8ce059e79d · outbound
This paper cites Self-Rewarding Language Models.
More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges Self-Rewarding Language Models
Reference 13
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-08T21:25:38.628686Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 673ffde6-90b0-4138-9369-886aaa53056e · outbound
This paper cites Generative Verifiers: Reward Modeling as Next-Token Prediction.
More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges Generative Verifiers: Reward Modeling as Next-Token Prediction
Reference 14
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-08T21:25:38.631126Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 23382bfc-ab7b-4f1b-95f5-22557924239b · outbound
This paper cites Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena.
More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
Reference 15
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-08T21:25:38.657623Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 9f584040-5632-4e7d-8caa-742fc0662be9 · outbound
This paper cites My answer:.
More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges My answer:
Reference 16
- Resolution
- malformed identifier
- raw_fallback, observed 2026-07-08T21:25:38.776124Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation dd5d18f7-6d21-4e60-851b-7e93d26be757 · outbound
This paper cites an unresolved cited work.
More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges Unresolved cited work
Reference 17
- Resolution
- verified exact
- arxiv_id, observed 2026-07-08T21:25:38.640934Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Pith citing papers
Observation 6ae011a9-146e-4fe1-beee-c62444a77711 · inbound
When the Reward Suite Is Leaky: A Preregistered Causal Contrast of Natural Verifier False Positives in RLVR cites this paper.
When the Reward Suite Is Leaky: A Preregistered Causal Contrast of Natural Verifier False Positives in RLVR More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges
Reference 42
- Resolution
- unresolved
- no resolver link, observed 2026-07-14T07:36:47.336670Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c00c37c5-f72f-4540-aa54-4c93eb9684bd · inbound
LLM-as-a-Judge Scores Are Unreliable Optimization Signals in Closed-Loop Table Recognition cites this paper.
LLM-as-a-Judge Scores Are Unreliable Optimization Signals in Closed-Loop Table Recognition More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges
Reference 45
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T05:30:04.547511Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.