Paper Citation Record · LEDGER

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study

As of 19 August 2026, this Paper Citation Record lists 64 of 64 outbound references and 1 inbound Pith citation observation for arXiv:2505.02142.

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

pith.paper-citation-record.v1
2505.02142 v1

Coverage vector

measured 64 of 64 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T01:04:38.905912Z

measured 65 of 65 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-26T12:15:08.304150Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T08:09:40.573829Z

Reference resolution

64 of 64 outbound references displayed

verified exact0
verified fuzzy7
unresolved56
parse uncertain1
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation cfc6ffb7-03ba-4eba-9fd6-71af80d16ba8 · outbound

This paper cites Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.684571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21aaef41-7ec3-4365-960b-e84b79d8d4a6 · outbound

This paper cites 2023 AMC 8 Problems/Problem 10.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study 2023 AMC 8 Problems/Problem 10

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.688977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e60a095f-4414-472f-a3bc-0f3766cc8b3e · outbound

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

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.696928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfb5a672-30d7-486a-87c1-6d3faeed708a · outbound

This paper cites Aime_1983_2024 (revision 6283828), 2025.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Aime_1983_2024 (revision 6283828), 2025

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:04:39.509068Z

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 b981d4f7-0535-4099-aa09-7de0a0976236 · outbound

This paper cites KTO: Model Alignment as Prospect Theoretic Optimization.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study KTO: Model Alignment as Prospect Theoretic Optimization

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.704305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c03598fa-80d8-423c-80a7-12c5a4bc109c · outbound

This paper cites Open r1: A fully open reproduction of deepseek-r1, January 2025.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Open r1: A fully open reproduction of deepseek-r1, January 2025

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.707916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfd2a199-21d7-4047-b36c-e29037e716e8 · outbound

This paper cites IPO: Your Language Model is Secretly a Preference Classifier.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study IPO: Your Language Model is Secretly a Preference Classifier

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.711041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b043f8c1-2096-43e6-9b3c-ded5ad26ccf3 · outbound

This paper cites Fine flan: Seqio to parquet so you don’t have to.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Fine flan: Seqio to parquet so you don’t have to

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.714253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35edec94-921d-417f-8268-b5b7d7e4a3df · outbound

This paper cites Deepmath-103k: A large-scale, challenging, decontaminated, and verifiable mathematical dataset for advancing reasoning.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Deepmath-103k: A large-scale, challenging, decontaminated, and verifiable mathematical dataset for advancing reasoning

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:04:39.485870Z

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 36ba94a6-3d6c-401e-8be6-f05dc26f9909 · outbound

This paper cites Logic-701: A benchmark dataset for logical reasoning in english and russian.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Logic-701: A benchmark dataset for logical reasoning in english and russian

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.720852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8acd92c1-cf25-489f-b27b-1220df8292fa · outbound

This paper cites OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.723914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d021b717-b790-4671-a5ca-0bb263ddb1a9 · outbound

This paper cites LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.727591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42d522cd-ce98-4ee4-b609-2adaff4b37ad · outbound

This paper cites Ncert biology 11th dataset.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Ncert biology 11th dataset

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.731892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c94e6c7e-6def-4fae-854b-0f554c700c60 · outbound

This paper cites Ncert biology 12th dataset.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Ncert biology 12th dataset

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.735710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7ef0b56-65a4-4d23-b65e-da49396f755d · outbound

This paper cites Ncert chemistry 11th dataset.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Ncert chemistry 11th dataset

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.738934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6bead1f-4387-4d28-bc3e-50f346df2916 · outbound

This paper cites Ncert chemistry 12th dataset.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Ncert chemistry 12th dataset

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.742197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cde3bd2-2c7e-4634-8363-63f554372d81 · outbound

This paper cites Ncert physics 11th dataset.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Ncert physics 11th dataset

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.746718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0bbfb90-8d5d-4a05-98d5-fa4f063b1e26 · outbound

This paper cites Ncert physics 12th dataset.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Ncert physics 12th dataset

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:04:39.439637Z

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 e9709543-80d9-4672-8f4b-5cca0aa9c277 · outbound

This paper cites Miranda, Alisa Liu, Nouha Dziri, Shane Lyu, Yuling Gu, Saumya Malik, Victoria Graf, Jena D.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Miranda, Alisa Liu, Nouha Dziri, Shane Lyu, Yuling Gu, Saumya Malik, Victoria Graf, Jena D

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.753815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52f0d26b-1f39-4ea6-8f0c-0cafd8564693 · outbound

This paper cites Tulu 3: Pushing Frontiers in Open Language Model Post-Training.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.756644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f43b0eef-f44c-4906-9d5a-7d44d721057b · outbound

This paper cites Numinamath.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Numinamath

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.759853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f863bc1-17ab-45ff-af56-419ba43e37e8 · outbound

This paper cites From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.762722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea88edfd-e382-4f14-a47f-eafaec48804a · outbound

This paper cites Gonzalez, and Ion Stoica.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Gonzalez, and Ion Stoica

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:04:39.416887Z

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 b7ce3c49-d795-499a-a456-2ee1ea860d6c · outbound

This paper cites Openorca: An open dataset of gpt augmented flan reasoning traces.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Openorca: An open dataset of gpt augmented flan reasoning traces

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.769300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64020ec3-470c-4727-8ea9-87132461dc8b · outbound

This paper cites Kw-r1: A simple implementation of the grpo algorithm.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Kw-r1: A simple implementation of the grpo algorithm

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:04:39.400427Z

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 facd71f4-229c-44e6-a287-0e06394fdd04 · outbound

This paper cites Length Desensitization in Direct Preference Optimization.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Length Desensitization in Direct Preference Optimization

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.778559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0670d9b8-4713-456d-be9f-fabe8423b899 · outbound

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

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Understanding R1-Zero-Like Training: A Critical Perspective

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.781933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d431f0b3-a664-4330-8609-ed74c031d357 · outbound

This paper cites an unresolved cited work.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-16T01:04:39.390630Z

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 0577ce0a-83a9-4fd4-8c11-5b7329c71616 · outbound

This paper cites Le, Barret Zoph, Jason Wei, and Adam Roberts.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Le, Barret Zoph, Jason Wei, and Adam Roberts

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.789797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b1d1f10-5720-4b46-91d9-c527e7e721a9 · outbound

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

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Deepcoder: A fully open-source 14b coder at o3-mini level

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.793190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54d018df-6ac2-4545-910f-3acbebc95abd · outbound

This paper cites Chemistry-qa.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Chemistry-qa

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.796500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd907a48-355e-4704-a676-b64958b1a11b · outbound

This paper cites s1: Simple test-time scaling.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study s1: Simple test-time scaling

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.799528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cc0aef8-6577-47a1-b6ba-dcb9d7ec331b · outbound

This paper cites Llama-nemotron-post-training-dataset.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Llama-nemotron-post-training-dataset

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:04:39.361345Z

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 bb9b5037-b839-4a3c-af70-4eeb96a5a5f1 · outbound

This paper cites Llama-3_1-nemotron-ultra-253b-v1.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Llama-3_1-nemotron-ultra-253b-v1

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.806310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b60eb25-de3b-4dd7-86bc-e3098757d1da · outbound

This paper cites Infinity instruct.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Infinity instruct

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.809759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65cd8540-6e1e-410f-becc-2038e4d44abf · outbound

This paper cites Verifiable coding problems (python).

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Verifiable coding problems (python)

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.813326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5be56665-1c51-4312-bc76-20fb0449a1ad · outbound

This paper cites Learning to reason with llms, 2024.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Learning to reason with llms, 2024

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.816799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e5fa7e0-01f8-4933-8485-2132de1b6538 · outbound

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

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Training language models to follow instructions with human feedback

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.820093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b7aec5e-ab2b-41de-9601-c70744877383 · outbound

This paper cites Codeforces cots.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Codeforces cots

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.823918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c50da048-1071-44d1-9016-a30d6181b3a2 · outbound

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

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Direct preference optimization: Your language model is secretly a reward model

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.827452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 753f0b64-6e9e-460c-bbda-031399d893e8 · outbound

This paper cites GPQA: A Graduate-Level Google-Proof Q&A Benchmark.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study GPQA: A Graduate-Level Google-Proof Q&A Benchmark

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.830986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92d7cc52-07a7-4321-8c8e-0a0355e26dd9 · outbound

This paper cites an unresolved cited work.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Unresolved cited work

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.834346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd0549cc-770a-4436-92f5-61b169cc9406 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Proximal Policy Optimization Algorithms

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.837931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f086508c-8213-4813-b586-6bda26b8ad29 · outbound

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

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.841121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3debcc52-d762-4f34-b563-ec1ec39d6de5 · outbound

This paper cites Qwen2.5: A party of foundation models, September 2024.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Qwen2.5: A party of foundation models, September 2024

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.844397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0348ce26-7209-4680-9726-41fb111acac4 · outbound

This paper cites Wizardlm evol-instruct 70k dataset.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Wizardlm evol-instruct 70k dataset

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.847460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47c34423-45bb-4bc5-a98d-66f46ff80514 · outbound

This paper cites Openhermes 2.5: An open dataset of synthetic data for generalist llm assistants, 2023.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Openhermes 2.5: An open dataset of synthetic data for generalist llm assistants, 2023

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.850481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eedb6bee-05fb-4a92-a0c7-7f105e290fa1 · outbound

This paper cites DeepDistill: Enhancing LLM Reasoning Capabilities via Large-Scale Difficulty-Graded Data Training.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study DeepDistill: Enhancing LLM Reasoning Capabilities via Large-Scale Difficulty-Graded Data Training

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.853466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba424970-494b-490e-8b2f-b9ed22ca704a · outbound

This paper cites Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.856568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91904807-967f-4db1-86cd-37e533561d43 · outbound

This paper cites Smith, Hannaneh Hajishirzi, and Daniel Khashabi.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Smith, Hannaneh Hajishirzi, and Daniel Khashabi

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.859743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec7a51fd-cdcc-4664-bd13-e3da0b781e75 · outbound

This paper cites Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.862534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1257ba9-7fda-4218-8b8a-3b8827da053e · outbound

This paper cites KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.865499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc608c9c-c12e-4716-ad8f-1e5d2a0f5d7b · outbound

This paper cites Qwen2 Technical Report.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Qwen2 Technical Report

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.868464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4daa4ef2-7916-475e-a215-45761ca69b20 · outbound

This paper cites MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.872002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0ff78bd-e467-4fe8-89fa-d8e224d68732 · outbound

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

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.875723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 965369bd-dfbd-4177-bbed-3666517ad2ce · outbound

This paper cites Free Process Rewards without Process Labels.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Free Process Rewards without Process Labels

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.879469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88222009-4be8-4abc-9e76-f8086dd15721 · outbound

This paper cites Naturalreasoning: Rea- soning in the wild with 2.8m challenging questions, 2025.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Naturalreasoning: Rea- soning in the wild with 2.8m challenging questions, 2025

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.883074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58731850-bb23-41c3-8764-5e480bd74fcd · outbound

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

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.886277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dab8b0b-d2ba-43d3-8881-a4ecc0b15ec3 · outbound

This paper cites CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.890403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe5866d2-194b-4ebb-9a3c-9d3b314333ff · outbound

This paper cites InfinityMATH: A Scalable Instruction Tuning Dataset in Programmatic Mathematical Reasoning.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study InfinityMATH: A Scalable Instruction Tuning Dataset in Programmatic Mathematical Reasoning

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.893490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e271105-5461-4e7d-a69e-1c64742f4812 · outbound

This paper cites Beyond IID: Optimizing Instruction Learning from the Perspective of Instruction Interaction and Dependency.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Beyond IID: Optimizing Instruction Learning from the Perspective of Instruction Interaction and Dependency

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.896787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b05ddc4c-e6e0-44d5-8d31-9137448fea7e · outbound

This paper cites Instruction-Following Evaluation for Large Language Models.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Instruction-Following Evaluation for Large Language Models

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-16T01:04:38.900467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dbfd169-9ebf-4bf4-937a-9d09a617fa74 · outbound

This paper cites Hey Siri.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Hey Siri

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T01:04:39.275023Z

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 07956d67-68b3-43fc-9354-a4ca7e89ccda · outbound

This paper cites an unresolved cited work.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study Unresolved cited work

Reference 2023

Resolution: parse uncertain; no resolver link, observed 2026-08-16T01:04:38.693266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 10c0d3fa-2308-45cb-9039-12172632c9c6 · inbound

Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning cites this paper.

Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study

Reference 204

Resolution: verified exact; arxiv_id, observed 2026-07-04T08:09:40.575141Z

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.