Paper Citation Record · LEDGER

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO

As of 23 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2605.30789.

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

pith.paper-citation-record.v1
2605.30789 v2

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-28T23:54:32.621093Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

33 of 33 outbound references displayed

verified exact26
verified fuzzy0
unresolved3
parse uncertain0
malformed identifier0
metadata mismatch4

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e5184e25-d6fb-4bbd-a786-56bd3bfbc711 · outbound

This paper cites H., Gendler, A., Baruch, E.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO H., Gendler, A., Baruch, E

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-28T23:54:32.621093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfdad6d3-10ef-46a2-bef7-a27be517981d · outbound

This paper cites MathArena: Evaluating LLMs on Uncontaminated Math Competitions.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO MathArena: Evaluating LLMs on Uncontaminated Math Competitions

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:02:49.955865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5678be66-f935-438d-b473-6875f7e76362 · outbound

This paper cites XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:02:49.999721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation cee07469-cbc6-4be3-ba94-bfd7660981d9 · outbound

This paper cites Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-06-29T00:02:49.994111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation cbcfb6d9-d078-4531-8dc4-62f770210d5b · outbound

This paper cites InternLM2 Technical Report.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO InternLM2 Technical Report

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:02:50.016446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation dbdbb877-69c4-4293-960d-ff94d5e1a27a · outbound

This paper cites arXiv preprint arXiv:2505.09655 , year=.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO arXiv preprint arXiv:2505.09655 , year=

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-06-29T00:02:50.013894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a6dbc338-87b0-4128-8cd4-667a5b19763e · outbound

This paper cites Jackpot: Optimal budgeted rejection sampling for extreme actor-policy discrep- ancy.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO Jackpot: Optimal budgeted rejection sampling for extreme actor-policy discrep- ancy

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T00:02:49.992299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b0bb883e-4a60-4bb8-bfc1-db939bbe8524 · outbound

This paper cites Soft Adaptive Policy Optimization.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO Soft Adaptive Policy Optimization

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:02:50.005480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 34c1a450-5466-497c-be0a-2b225c0a4981 · outbound

This paper cites Minillm: Knowl- edge distillation of large language models.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO Minillm: Knowl- edge distillation of large language models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-28T23:54:32.621093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8ea111c-6918-4653-8877-3d35b65f6623 · outbound

This paper cites GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-06-29T00:02:49.977641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 877c50ac-8167-4cef-bc55-0d4066c5986e · outbound

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

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:02:49.927751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e65d567a-c42f-4869-a487-3b2fea9c97ff · outbound

This paper cites Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:02:49.943309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9cf8a0d8-343e-48f9-8834-0ff07d2702ba · outbound

This paper cites OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems

Reference 13

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T00:02:49.930578Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2d32e68f-3b47-4b32-8ab0-b5f12967a60d · outbound

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

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO Measuring Mathematical Problem Solving With the MATH Dataset

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:02:49.999456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f8108edc-e84b-4b92-abd4-9be625991368 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO Distilling the Knowledge in a Neural Network

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:02:50.008144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2f1e0915-0195-4718-ac64-e0c8493060fa · outbound

This paper cites ORPO: Monolithic Preference Optimization without Reference Model.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO ORPO: Monolithic Preference Optimization without Reference Model

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:02:50.005155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 30cc35bc-d992-49a3-977c-09b4320d912e · outbound

This paper cites Qerl: Beyond efficiency– quantization-enhanced reinforcement learning for llms.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO Qerl: Beyond efficiency– quantization-enhanced reinforcement learning for llms

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-06-29T00:02:50.011057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5a3bc79c-67c2-4a6c-9464-b222eb19007a · outbound

This paper cites Revisiting Entropy in Reinforcement Learning for Large Reasoning Models.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO Revisiting Entropy in Reinforcement Learning for Large Reasoning Models

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:02:49.991625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b75fb654-4b5b-422b-90b6-17d0088be00e · outbound

This paper cites A survey of reinforcement learning from human feedback.arXiv preprint arXiv:2312.14925.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO A survey of reinforcement learning from human feedback.arXiv preprint arXiv:2312.14925

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-06-29T00:02:49.997022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7465628b-7cca-4c32-8f66-7c8684b401f7 · outbound

This paper cites Bridging Offline and Online Reinforcement Learning for LLMs.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO Bridging Offline and Online Reinforcement Learning for LLMs

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-06-29T00:02:50.010858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a4016e76-460e-4422-a3b5-7515261b4ea6 · outbound

This paper cites Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-06-29T00:02:49.986417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4561501a-a758-465f-99a2-04e64f88cb82 · outbound

This paper cites Revisiting Group Relative Policy Optimization: Insights into On-Policy and Off-Policy Training.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO Revisiting Group Relative Policy Optimization: Insights into On-Policy and Off-Policy Training

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-06-29T00:02:50.008096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation acb52fa1-ebfd-4aca-a3c6-894ff4fcae75 · outbound

This paper cites N., Baker, A., Neo, C., Roush, A., Kirsch, A., and Shwartz-Ziv, R.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO N., Baker, A., Neo, C., Roush, A., Kirsch, A., and Shwartz-Ziv, R

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-06-29T00:02:49.965115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 71d18420-4c65-4d7f-b1aa-5832cc82b84f · outbound

This paper cites Proximal Policy Optimization Algorithms.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO Proximal Policy Optimization Algorithms

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:02:49.994581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f09f70c8-c90a-4d02-8d65-37e642f77bc8 · outbound

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

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:02:49.974561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 41debccd-ddd4-44db-af2c-9b54ce718dbe · outbound

This paper cites HybridFlow: A Flexible and Efficient RLHF Framework.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO HybridFlow: A Flexible and Efficient RLHF Framework

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:02:49.982521Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 807a29ab-7504-4fbb-90be-3cbbad3e2165 · outbound

This paper cites Unchosen experts can contribute too: Unleashing moe models’ power by self-contrast.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO Unchosen experts can contribute too: Unleashing moe models’ power by self-contrast

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-28T23:54:32.621093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7b14d4f-91b1-4a2d-808d-11550e860520 · outbound

This paper cites SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training

Reference 28

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T00:02:49.965076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7b9f45e6-bdd6-4685-9e04-d696d82f0e07 · outbound

This paper cites Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:02:50.002850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bf9d075f-f5e3-4959-85d5-4501d0fd92c0 · outbound

This paper cites and Zuo, C.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO and Zuo, C

Reference 30

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T00:02:49.977302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d573ebba-a89f-4ef3-9e76-5f893d5e3882 · outbound

This paper cites EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-06-29T00:02:49.989463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f290c786-bea9-40a4-8232-55794a183199 · outbound

This paper cites Group Sequence Policy Optimization.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO Group Sequence Policy Optimization

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:02:49.946076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 71cbf156-beb6-406f-a1d3-0c7dea7708d2 · outbound

This paper cites Exploring multi-temperature strategies for token-and rollout-level control in rlvr.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO Exploring multi-temperature strategies for token-and rollout-level control in rlvr

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-06-29T00:02:49.986252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Pith citing papers

No inbound Pith citation observations are available.