Paper Citation Record · LEDGER

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

As of 20 August 2026, this Paper Citation Record lists 53 of 53 outbound references and 15 inbound Pith citation observations for arXiv:2505.12929.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2505.12929 v1

Coverage vector

measured 53 of 53 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:29:01.735774Z

measured 68 of 68 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 15 of 15 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T22:52:02.124869Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-07-10T14:27:07.373132Z

Reference resolution

53 of 53 outbound references displayed

verified exact0
verified fuzzy24
unresolved28
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5526fc05-a027-4cc4-87c6-ddaddea30bdd · outbound

This paper cites OpenAI o1 System Card.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs OpenAI o1 System Card

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.471084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5406fdbb-4131-4219-b078-e436f69483f6 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.477574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a56aad7-552c-4c90-a4cc-73f0a93fef00 · outbound

This paper cites Kimi k1.5: Scaling Reinforcement Learning with LLMs.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.483089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 849d660e-a703-481c-a394-af141c2fa03e · outbound

This paper cites Monte carlo tree search boosts reasoning via iterative preference learning.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Monte carlo tree search boosts reasoning via iterative preference learning

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:29:02.636536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8918163f-31d7-4a78-a55c-f9f82be8e9ec · outbound

This paper cites Alphamath almost zero: Process su- pervision without process.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Alphamath almost zero: Process su- pervision without process

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:29:02.620104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 9da1503d-f1d6-4bd1-982f-54a9245f8d6a · outbound

This paper cites Let’s verify step by step.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Let’s verify step by step

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.500140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1598d75-938b-4f66-afa4-48079d76a431 · outbound

This paper cites Math-shepherd: Verify and reinforce llms step-by-step without human annotations.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Math-shepherd: Verify and reinforce llms step-by-step without human annotations

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:29:02.593102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 6bca8f1d-3e62-4948-9d66-ab6019275a4f · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.510372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05325b6c-6c2f-4ed9-b818-fd78ae52ee50 · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.515576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65b6a274-cf18-4d2e-a71f-f91342c50a10 · outbound

This paper cites Understanding R1-Zero-Like Training: A Critical Perspective.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Understanding R1-Zero-Like Training: A Critical Perspective

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.521431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ead49eaa-8eb3-46c2-b3bd-ebb996ea348c · outbound

This paper cites A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.530228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86589244-9023-4876-b9c9-048fc525436b · outbound

This paper cites Deep reinforcement learning from human preferences.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Deep reinforcement learning from human preferences

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:29:02.578463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation eb4ed842-0e90-48ff-81a3-24067ce60bff · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Fine-Tuning Language Models from Human Preferences

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.540427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fff14750-b579-4fef-8a0f-808dd0f1ef5c · outbound

This paper cites Learning to summarize with human feedback.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Learning to summarize with human feedback

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:29:02.563031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 19befe5b-abac-4da2-b8f0-3019168b228a · outbound

This paper cites Training language models to follow instructions with human feedback.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Training language models to follow instructions with human feedback

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:29:02.548096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 6f80dba7-3e47-4faf-9b55-d81fbd7307fb · outbound

This paper cites Proximal Policy Optimization Algorithms.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Proximal Policy Optimization Algorithms

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.555019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0eb6887-8369-4124-bfd6-94ab3d1cf39f · outbound

This paper cites Language models are few-shot learners.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Language models are few-shot learners

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:29:02.532709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d9dff6a3-44c1-4cc3-99c9-622bed19f749 · outbound

This paper cites GPT-4 Technical Report.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs GPT-4 Technical Report

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.565135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8721c4e6-4de0-400d-88e9-f525a519c028 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs LLaMA: Open and Efficient Foundation Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.570064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5494e24-675c-4573-9b1e-238c749465f7 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.574926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a37f115-ddb2-40c6-8dbd-f4c0800be69e · outbound

This paper cites The Llama 3 Herd of Models.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs The Llama 3 Herd of Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.579804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a5ae833-4b33-4c01-a70a-33b0528dfe75 · outbound

This paper cites Qwen Technical Report.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Qwen Technical Report

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.584511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 592b6e06-1238-4e85-a6d8-5d22647b2ba2 · outbound

This paper cites Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.589285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb40335f-8ec3-4346-905a-1d47c932203b · outbound

This paper cites Qwen2 Technical Report.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Qwen2 Technical Report

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.594462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c936a1ed-f186-4dc2-beef-6ff0e6f89a4d · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Gemini: A Family of Highly Capable Multimodal Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.599413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b64ba0f-edad-4a25-93c6-609c5fca5bf0 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.604503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e10b5731-abd3-4506-93b6-4454f4999754 · outbound

This paper cites The Claude 3 model family: Opus, sonnet, haiku.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs The Claude 3 model family: Opus, sonnet, haiku

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:29:02.516490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 70e37f1d-b0ac-4b72-90ed-508ec8d1f208 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Direct preference optimization: Your language model is secretly a reward model

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:29:02.500182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f45a84af-8051-43c6-9fe8-9a24b9753eb3 · outbound

This paper cites From r to Q*: Your language model is secretly a Q-function.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs From r to Q*: Your language model is secretly a Q-function

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:29:02.484484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 886ec526-8660-4ab8-8745-dd8ab8c30c4d · outbound

This paper cites Is DPO superior to PPO for LLM alignment? a comprehensive study.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Is DPO superior to PPO for LLM alignment? a comprehensive study

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:29:02.469600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation af302d94-5822-44ae-9f6e-1e4bc9e9000c · outbound

This paper cites DPO meets PPO: Reinforced token optimization for RLHF.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs DPO meets PPO: Reinforced token optimization for RLHF

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:29:02.453265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ca71bb59-21f8-4a8c-a71f-2b463adc45f9 · outbound

This paper cites Sutherland.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Sutherland

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:29:02.436839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 358cdf93-5346-44f3-85dc-ec67d831372a · outbound

This paper cites ORPO: Monolithic preference optimization without reference model.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs ORPO: Monolithic preference optimization without reference model

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:29:02.418963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b03a277f-c07d-4d39-9843-a34a48e52781 · outbound

This paper cites Contrastive preference optimization: Pushing the boundaries of llm performance in machine translation.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Contrastive preference optimization: Pushing the boundaries of llm performance in machine translation

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:29:02.402551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2598b004-24fb-4140-9093-fafc0e0d9354 · outbound

This paper cites SimPO: Simple preference optimization with a reference-free reward.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs SimPO: Simple preference optimization with a reference-free reward

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:29:02.386629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c609134d-aa82-41d7-b185-fd9961827394 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Chain-of-thought prompting elicits reasoning in large language models

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:29:02.370794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 382cad17-3053-43f5-b5a6-843a7bd4733f · outbound

This paper cites Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Li Erran Li, Raluca Ada Popa, and Ion Stoica.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Li Erran Li, Raluca Ada Popa, and Ion Stoica

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:29:02.354290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c454f95f-1eff-4265-8ec9-d772c025551e · outbound

This paper cites Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.662434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f56f0902-ac21-4a42-b8e3-70542325af25 · outbound

This paper cites Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.668030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be9b3875-e80d-41f1-99ae-44df00a5b9fa · outbound

This paper cites SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.673051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3a2ab91-fd47-4fbf-be6b-6453c3378dc6 · outbound

This paper cites VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.677994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 678ca9be-48c7-41f6-9b1e-2c2002903985 · outbound

This paper cites Efficient Reinforcement Finetuning via Adaptive Curriculum Learning.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Efficient Reinforcement Finetuning via Adaptive Curriculum Learning

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.683537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d493bbd5-ac1e-424f-ad86-3f04f77d726a · outbound

This paper cites Attention is all you need.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Attention is all you need

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.688332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7c8b96d-491a-4a48-9c27-be32b1f6ca01 · outbound

This paper cites Hybridflow: A flexible and efficient RLHF framework.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Hybridflow: A flexible and efficient RLHF framework

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:29:02.327951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 778f7272-2792-4308-8ac7-820d26be5555 · outbound

This paper cites On Memorization of Large Language Models in Logical Reasoning.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs On Memorization of Large Language Models in Logical Reasoning

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.697399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd308106-049f-4688-bc4d-c98e4417cb56 · outbound

This paper cites REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.702314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbf63c99-bd86-4c73-b8d2-e1b74458d0fb · outbound

This paper cites What is the name of this book? Touchstone Books Guildford, UK, 1986.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs What is the name of this book? Touchstone Books Guildford, UK, 1986

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:29:02.311449Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 166b8592-9003-4ddd-b4ad-2f844a56be24 · outbound

This paper cites Meta-logical problems: Knights, knaves, and rips.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Meta-logical problems: Knights, knaves, and rips

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:29:02.293570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation dc81e272-2755-4b6f-8cba-3e83b7eeea38 · outbound

This paper cites Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:29:02.277686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1f3f9c9a-d5b5-41ca-b292-f76012178bd4 · outbound

This paper cites Solving quantitative reasoning problems with language models.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Solving quantitative reasoning problems with language models

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:29:02.260729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2c0a9a57-5372-4268-9459-0029ae0f16da · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Measuring Mathematical Problem Solving With the MATH Dataset

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-15T20:29:01.726086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bcb8349-f2d1-4a3a-a853-68f3fa746092 · outbound

This paper cites Approximating KL divergence.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Approximating KL divergence

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:29:02.244387Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 92e56b54-cf11-41e8-9be7-e9594d427974 · outbound

This paper cites Lily is a knave or Lily is a knight.

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs Lily is a knave or Lily is a knight

Reference 53

Resolution: malformed identifier; raw_fallback, observed 2026-08-15T20:29:02.226983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Pith citing papers

Observation e4be3531-b861-4d71-b485-7ec46ae5d5d7 · inbound

Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR cites this paper.

Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

Reference 48

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T23:24:26.303073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c743253d-9e0d-4fdb-aa86-b63a49ff7c4e · inbound

Sharpness-Guided Group Relative Policy Optimization via Probability Shaping cites this paper.

Sharpness-Guided Group Relative Policy Optimization via Probability Shaping Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-18T03:12:22.271239Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 02ac3733-2f36-4d5f-8fbe-047402cdfd01 · inbound

STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens cites this paper.

STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-15T21:46:43.296750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation cad0b166-4da6-4db6-a43a-72de0c98a855 · inbound

STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens cites this paper.

STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T22:52:02.124869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 648c269a-14bd-455c-a677-c86f9c05996b · inbound

GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning cites this paper.

GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-10T00:14:46.307201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4c3acee1-4909-4b4f-968c-40287fac6581 · inbound

Holder Policy Optimisation cites this paper.

Holder Policy Optimisation Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:12:22.793408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ea8c1185-787b-401f-98a2-5f755ff490cd · inbound

Holder Policy Optimisation cites this paper.

Holder Policy Optimisation Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:01:22.958441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 6a685f5c-6fd3-43b6-8ad2-5f37239a67b5 · inbound

Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation cites this paper.

Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

Reference 44

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T06:09:41.284703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b10868ed-2f85-4319-9de5-65ce2c902b99 · inbound

Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation cites this paper.

Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

Reference 44

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T15:15:47.303183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 131054e5-b69f-4763-ab6b-3bc8dd993145 · inbound

Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals cites this paper.

Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:51:15.632516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation fd100329-ae05-43c5-ba78-30f6b5c19ba2 · inbound

Not only where, But when: Temporal Scheduling for RLVR cites this paper.

Not only where, But when: Temporal Scheduling for RLVR Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-06-29T22:44:01.829569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 76058b5a-fb62-4cd7-ac8a-b0925351b827 · inbound

Trust Region On-Policy Distillation cites this paper.

Trust Region On-Policy Distillation Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

Reference 239

Resolution: verified exact; arxiv_id, observed 2026-07-01T20:56:13.433277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d296df5d-1a88-43d9-bdd4-bdf8708b5267 · inbound

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning cites this paper.

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

Reference 124

Resolution: verified exact; arxiv_id, observed 2026-07-03T20:38:55.893132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation af7bf6e4-7168-4bd3-8cb3-3bc0f4d082bd · inbound

What are Key Factors for Updates in RL for LLM Reasoning? cites this paper.

What are Key Factors for Updates in RL for LLM Reasoning? Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-07-04T09:09:43.578480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation de480b0e-a72d-4343-9e30-f44cbd760865 · inbound

When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning cites this paper.

When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-07-10T14:27:07.374977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.