Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-09T22:55:19.471307Z
Paper Citation Record · LEDGER
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning
As of 7 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2604.21327.
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 2026-08-06T06:34:29.942622+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
22 of 22 outbound references displayed
- verified exact5
- verified fuzzy3
- unresolved1
- parse uncertain0
- malformed identifier0
- metadata mismatch13
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 993bcdb0-e451-4784-979e-d0e3b9e60613 · outbound
This paper cites AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning.
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning
Reference 1
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T14:16:07.278352Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 853382d8-ffd6-40b4-895e-ebe07bbe1ab0 · outbound
This paper cites The Llama 3 Herd of Models.
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning The Llama 3 Herd of Models
Reference 2
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T14:16:07.310219Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 7e8e9d1e-c1e8-4ce8-96c1-20ca7ff6416e · outbound
This paper cites OpenAI o1 System Card.
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning OpenAI o1 System Card
Reference 3
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T14:16:07.142595Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation b004abd2-4277-4aac-99f7-ca41408c70fb · outbound
This paper cites Tulu 3: Pushing Frontiers in Open Language Model Post-Training.
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning Tulu 3: Pushing Frontiers in Open Language Model Post-Training
Reference 4
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T14:16:07.154064Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 9a1177b7-7814-4e81-a5e1-4ebf023f189a · outbound
This paper cites ETTRL: Balancing Exploration and Exploitation in LLM Test-Time Reinforcement Learning Via Entropy Mechanism.
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning ETTRL: Balancing Exploration and Exploitation in LLM Test-Time Reinforcement Learning Via Entropy Mechanism
Reference 5
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T14:16:07.228056Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 7838304b-0556-4016-b531-a576edb2b8a6 · outbound
This paper cites Maximizing Confidence Alone Improves Reasoning.
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning Maximizing Confidence Alone Improves Reasoning
Reference 6
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T14:16:07.165280Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 53c6ef3a-5f2d-43e1-8940-52451893aa05 · outbound
This paper cites Qwen2.5 Technical Report.
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning Qwen2.5 Technical Report
Reference 7
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T14:16:07.195702Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 22c26f1a-5272-4615-b067-806161e7cc74 · outbound
This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Reference 8
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T14:16:07.358998Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 4ada04d9-6c8e-46a0-91d7-b097450ce33d · outbound
This paper cites HybridFlow: A Flexible and Efficient RLHF Framework.
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning HybridFlow: A Flexible and Efficient RLHF Framework
Reference 9
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T14:16:07.329408Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 3272d8e9-62e4-4bc8-95aa-6b7d80aaa11b · outbound
This paper cites Associated with the WaltonFuture GeoQA-8K-direct-synthesizing dataset release.
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning Associated with the WaltonFuture GeoQA-8K-direct-synthesizing dataset release
Reference 10
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T14:16:07.183229Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation ebf84b02-b72e-442b-848c-bd800b138f27 · outbound
This paper cites Dong Yan, Gaochen Wu, and Bowen Zhou.
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning Dong Yan, Gaochen Wu, and Bowen Zhou
Reference 11
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T14:16:07.336008Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a2c8f175-abc0-4a88-ac49-bc7f09d574ca · outbound
This paper cites Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement.
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
Reference 12
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T14:16:07.343427Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation df0842d8-0d3e-4837-bc14-c47570cad3ec · outbound
This paper cites Benchmarking Test-Time Adaptation against Distribution Shifts in Image Classification.
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning Benchmarking Test-Time Adaptation against Distribution Shifts in Image Classification
Reference 13
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T14:16:07.318067Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 1b1d1d6c-e1c3-4414-b792-8952e4fd56f8 · outbound
This paper cites Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models.
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models
Reference 14
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T14:16:07.293158Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 40296b30-7cb6-48b9-a5ba-682c59888317 · outbound
This paper cites Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?.
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
Reference 15
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T14:16:07.352061Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 98c45d61-939f-4e99-8b5e-db97e61b2730 · outbound
This paper cites Cumulative Reasoning with Large Language Models.
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning Cumulative Reasoning with Large Language Models
Reference 16
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-15T02:43:16.267428Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 47ac53db-7c7a-400f-857d-031e7774a745 · outbound
This paper cites Learning to Reason without External Rewards.
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning Learning to Reason without External Rewards
Reference 17
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-15T21:16:57.297836Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 02984892-d7eb-4381-9052-b90a5366d86d · outbound
This paper cites TTRL: Test-Time Reinforcement Learning.
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning TTRL: Test-Time Reinforcement Learning
Reference 18
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T14:16:07.213973Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 636bcd7c-dbdc-41d3-9723-ce41cf498bfe · outbound
This paper cites an unresolved cited work.
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning Unresolved cited work
Reference 19
- Resolution
- unresolved
- raw_fallback, observed 2026-05-23T13:58:02.718328Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a352f429-65b4-483a-8dec-1fb65aad2099 · outbound
This paper cites This confirms that the key assump- tion behind BCS is not specific to MATH-500 but generalizes to other datasets.
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning This confirms that the key assump- tion behind BCS is not specific to MATH-500 but generalizes to other datasets
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T13:58:02.714862Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation cf37b11c-444c-4623-b886-3433621892fb · outbound
This paper cites To investigate the impact of the refinement size on model performance, we conduct a sensitivity analysis by scaling the original setting (1x) to 2x and 4x Table.
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning To investigate the impact of the refinement size on model performance, we conduct a sensitivity analysis by scaling the original setting (1x) to 2x and 4x Table
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T13:58:02.707784Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 377fa298-9343-4b83-9f0b-a11375230cce · outbound
This paper cites Scaling up the refinement size yields highly marginal improvements across all benchmarks.
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning Scaling up the refinement size yields highly marginal improvements across all benchmarks
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-23T13:58:02.711142Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Pith citing papers
No inbound Pith citation observations are available.