Paper Citation Record · LEDGER

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training

As of 19 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 10 inbound Pith citation observations for arXiv:2507.12507.

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

pith.paper-citation-record.v1
2507.12507 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T16:51:43.099838Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 10 of 10 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T18:21:08.555405Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T20:56:13.554863Z

Reference resolution

33 of 33 outbound references displayed

verified exact0
verified fuzzy14
unresolved19
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 01702ac7-f90e-41df-ad01-e3366eed0b87 · outbound

This paper cites OpenAI o1 System Card.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training OpenAI o1 System Card

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T16:51:41.308878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b91c1ff4-f3e1-4e84-836e-c7ef764722fb · outbound

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

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T16:51:41.379398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cd6446e-a56c-4d76-832e-a6d630ed29b0 · outbound

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

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Tang, Manan Roongta, Colin Cai, Jef- frey Luo, Li Erran Li, Raluca Ada Popa, and Ion Stoica

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:51:44.536753Z

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 ae443173-a672-4bb6-87ec-464a477d3bef · outbound

This paper cites Dapo: An open-source llm reinforcement learning system at scale, 2025.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Dapo: An open-source llm reinforcement learning system at scale, 2025

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T16:51:41.605352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d72de7c8-7f04-4e43-b906-ee8f2bc20d39 · outbound

This paper cites Process Reinforcement through Implicit Rewards.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Process Reinforcement through Implicit Rewards

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T16:51:41.675432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3eded81-4d23-4ab7-abbf-2568a743311f · outbound

This paper cites Scp-116k: A high-quality problem-solution dataset and a generalized pipeline for automated extraction in the higher education science domain, 2025.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Scp-116k: A high-quality problem-solution dataset and a generalized pipeline for automated extraction in the higher education science domain, 2025

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T16:51:41.754532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7202fe5-07b3-4c21-8477-6aec33c4b1fc · outbound

This paper cites Reasoning gym: Reasoning environments for reinforcement learning with verifiable rewards, 2025.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Reasoning gym: Reasoning environments for reinforcement learning with verifiable rewards, 2025

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:51:44.440037Z

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 e2d45004-e28f-4f90-b895-4a4bf75b0781 · outbound

This paper cites an unresolved cited work.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-06T16:51:44.361140Z

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 6c2e0656-9b38-4af2-8d61-d9e6fb88c713 · outbound

This paper cites Instruction-following evaluation for large language models, 2023.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Instruction-following evaluation for large language models, 2023

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T16:51:41.986503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73910816-2529-43d4-ba57-7b29a62e8611 · outbound

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

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T16:51:42.072510Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38a9ed1a-7369-4098-9a0b-75cbc62aa494 · outbound

This paper cites Proximal policy optimization algorithms, 2017.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Proximal policy optimization algorithms, 2017

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T16:51:42.132236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44a62020-97b4-44bf-b019-693d73a66d65 · outbound

This paper cites Approximating KL Divergence.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Approximating KL Divergence

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:51:44.270150Z

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 e9f94756-acd8-4fa3-9f76-d3a664121d0b · outbound

This paper cites Deepcoder: A fully open-source 14b coder at o3-mini level.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Deepcoder: A fully open-source 14b coder at o3-mini level

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:51:44.190811Z

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 5036a461-add3-44f6-971b-82c784a0fff8 · outbound

This paper cites Vapo: Efficient and reliable reinforcement learning for advanced reasoning tasks, 2025.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Vapo: Efficient and reliable reinforcement learning for advanced reasoning tasks, 2025

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:51:44.120691Z

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 06296c41-5472-4ca1-a519-acb330813ae0 · outbound

This paper cites Skywork open reasoner series.https://capricious-hydrogen-41c .notion.site/Skywork-Open-Reaonser- Series-1d0bc9ae823a80459b46c149e4f51680, 2025.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Skywork open reasoner series.https://capricious-hydrogen-41c .notion.site/Skywork-Open-Reaonser- Series-1d0bc9ae823a80459b46c149e4f51680, 2025

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:51:44.066802Z

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 9fb672b9-d13d-4e17-97ff-e2bb93fea91c · outbound

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

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Hybridflow: A flexible and efficient rlhf framework

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:51:43.928142Z

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 1f6e9583-fd27-417e-ae19-f98d530e3e09 · outbound

This paper cites Decoupled weight decay regularization, 2019.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Decoupled weight decay regularization, 2019

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T16:51:42.428615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4371198a-3b07-42c5-a489-2af2baca32d0 · outbound

This paper cites 7b model and 8k examples: Emerging reasoning with reinforcement learning is both effective and efficient.https://hkust-nlp.notion.site/ simplerl-reason, 2025.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training 7b model and 8k examples: Emerging reasoning with reinforcement learning is both effective and efficient.https://hkust-nlp.notion.site/ simplerl-reason, 2025

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:51:43.806690Z

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 9ec5ac18-d477-4187-bdce-9003b7eb8312 · outbound

This paper cites American invitational mathematics examination - aime.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training American invitational mathematics examination - aime

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:51:43.711163Z

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 62f2ad05-1b60-44e6-b401-05a5ffa833e7 · outbound

This paper cites American invitational mathematics examination - aime.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training American invitational mathematics examination - aime

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:51:43.608952Z

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 ea63ccc2-ada3-4e43-b86d-47132b004ac6 · outbound

This paper cites American mathematics competition - amc.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training American mathematics competition - amc

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:51:43.543312Z

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 c7028bb1-2669-48a3-b27d-c54cbecb0cb6 · outbound

This paper cites Measuring mathematical problem solving with the math dataset, 2021.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Measuring mathematical problem solving with the math dataset, 2021

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T16:51:42.599645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bde776d0-36a9-4c99-a458-dfee812f1963 · outbound

This paper cites Solving quantitative reasoning problems with language models, 2022.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Solving quantitative reasoning problems with language models, 2022

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T16:51:42.633994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58383f93-4bd2-4994-9394-11a5d15a3604 · outbound

This paper cites Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems, 2024.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems, 2024

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T16:51:42.657244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43299953-156f-4e44-91f1-fd7833a838ea · outbound

This paper cites Measuring coding challenge competence with apps, 2021.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Measuring coding challenge competence with apps, 2021

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T16:51:42.719030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31cdb266-0bbe-4b21-ba0e-157ff5892789 · outbound

This paper cites Mankowitz, Esme Sutherland Robson, Pushmeet Kohli, Nando de Freitas, Koray Kavukcuoglu, and Oriol Vinyals.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Mankowitz, Esme Sutherland Robson, Pushmeet Kohli, Nando de Freitas, Koray Kavukcuoglu, and Oriol Vinyals

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T16:51:42.778292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12403a07-828b-4577-9316-ef7bc464d2d8 · outbound

This paper cites Taco: Topics in algorithmic code generation dataset, 2023.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Taco: Topics in algorithmic code generation dataset, 2023

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T16:51:42.831655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98a14543-e3ae-4cb7-bccf-8b9d918c770c · outbound

This paper cites Is your code generated by chatGPT really correct? rigorous evaluation of large language models for code generation.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Is your code generated by chatGPT really correct? rigorous evaluation of large language models for code generation

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:51:43.418470Z

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 ae44f13a-84c5-4e58-82bc-276933a6febe · outbound

This paper cites Livecodebench: Holistic and contamination free evaluation of large language models for code, 2024.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Livecodebench: Holistic and contamination free evaluation of large language models for code, 2024

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T16:51:42.887053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 202e4379-5d88-4739-af38-9804f644e500 · outbound

This paper cites an unresolved cited work.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T16:51:42.908581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0df78d3-4be0-4360-8fef-94fdf4fc1630 · outbound

This paper cites Online difficulty filtering for reasoning oriented reinforcement learning, 2025.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Online difficulty filtering for reasoning oriented reinforcement learning, 2025

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T16:51:42.984504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bba4a0ec-2391-4fa3-a991-b13230e25b7a · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training Gonzalez, Hao Zhang, and Ion Stoica

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:51:43.341473Z

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 3573b1db-f3f2-4d53-8cdc-f1b92d7d675d · outbound

This paper cites The curious case of neural text degeneration, 2020.

Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training The curious case of neural text degeneration, 2020

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:51:43.283087Z

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 fa18ef4b-7416-40ea-a7b3-0d7e23549957 · inbound

Revisiting LLM Reasoning via Information Bottleneck cites this paper.

Revisiting LLM Reasoning via Information Bottleneck Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:08.555405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74b92fd2-80fe-457e-8dfc-f7d363cc0b3b · inbound

Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies cites this paper.

Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T04:39:04.024925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da2f79da-b1fe-4b5c-bc8a-065e3102426e · inbound

Learning to Reason Efficiently with Discounted Reinforcement Learning cites this paper.

Learning to Reason Efficiently with Discounted Reinforcement Learning Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-04T07:59:53.046706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3310297e-1a88-4046-94cf-424c1b424a51 · inbound

Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models cites this paper.

Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:25:59.026410Z

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 ddab7b49-4cd9-47a9-8686-07871448f7bd · inbound

Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models cites this paper.

Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-12T22:48:45.647588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19e525d1-700f-4d79-b634-ea8bad51050a · inbound

Generalization in LLM Problem Solving: The Case of the Shortest Path cites this paper.

Generalization in LLM Problem Solving: The Case of the Shortest Path Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-10T10:39:38.040670Z

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 e5e3e00a-54c4-4420-88fc-74d3b10c6268 · inbound

DISA: Offline Importance Sampling for Distribution-Matching LLM-RL cites this paper.

DISA: Offline Importance Sampling for Distribution-Matching LLM-RL Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-20T15:13:24.864105Z

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 087dd9df-be03-46a5-a491-625313e27927 · inbound

ARES: Automated Rubric Synthesis for Scalable LLM Reinforcement Learning cites this paper.

ARES: Automated Rubric Synthesis for Scalable LLM Reinforcement Learning Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-25T04:35:21.594882Z

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 85b190e6-9899-4bb1-95db-2d694c32d13a · inbound

ARES: Automated Rubric Synthesis for Scalable LLM Reinforcement Learning cites this paper.

ARES: Automated Rubric Synthesis for Scalable LLM Reinforcement Learning Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-06-30T16:24:55.362639Z

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 373a9187-b9f6-4da7-8a24-f1581a8da92d · inbound

Trust Region On-Policy Distillation cites this paper.

Trust Region On-Policy Distillation Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training

Reference 226

Resolution: verified exact; arxiv_id, observed 2026-07-01T20:56:13.556324Z

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.