Paper Citation Record · LEDGER

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training

As of 7 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2605.12380.

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

pith.paper-citation-record.v1
2605.12380 v1

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-13T05:39:04.306845Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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

39 of 39 outbound references displayed

verified exact9
verified fuzzy27
unresolved2
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4c243dda-e7cb-451c-878d-e652851278d1 · outbound

This paper cites Amo-bench: Large language models still struggle in high school math competitions.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Amo-bench: Large language models still struggle in high school math competitions

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.146229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 71356322-f774-4891-b7e6-8a78977a6580 · outbound

This paper cites What matters for on-policy deep actor-critic methods? A large-scale study.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training What matters for on-policy deep actor-critic methods? A large-scale study

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.079693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 14d801f2-3185-4f2a-a32c-fa250507843a · outbound

This paper cites Bridging the training-inference gap in LLMs by leveraging self-generated tokens.Transactions on Machine Learning Research.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Bridging the training-inference gap in LLMs by leveraging self-generated tokens.Transactions on Machine Learning Research

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.003365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e713ee0d-d843-4a8d-88bc-adb122cdaa83 · outbound

This paper cites Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning.Nature, 645:633–638.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning.Nature, 645:633–638

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.083999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1ba607bc-0d2d-4c77-909d-a0e3b21c8406 · outbound

This paper cites Implementation matters in deep policy gradients: A case study on PPO and TRPO.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Implementation matters in deep policy gradients: A case study on PPO and TRPO

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.075355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b40fdd02-35e4-42ec-8e59-9fd7e789199a · outbound

This paper cites IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.066735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 354d4686-ca58-4f1e-8a32-0c34540e9f08 · outbound

This paper cites an unresolved cited work.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-05-13T10:17:39.046404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8f999cdf-f5d1-4288-90bf-0f3f34668aa1 · outbound

This paper cites DDPG++: Striving for Simplicity in Continuous-control Off-Policy Reinforcement Learning.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training DDPG++: Striving for Simplicity in Continuous-control Off-Policy Reinforcement Learning

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:42:21.015162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2e3b96a8-358f-4460-807b-976e67f738d6 · outbound

This paper cites an unresolved cited work.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-05-13T10:17:39.054682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 61e706a3-94d9-459b-8ae9-df42c4a0f63c · outbound

This paper cites Lipton, Pratik Chaudhari, and Alexander J.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Lipton, Pratik Chaudhari, and Alexander J

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.058601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 49cee8d0-dc64-45e9-afc4-145bdf1dc056 · outbound

This paper cites Continuous doubly constrained batch reinforcement learning.Advances in Neural Information Processing Systems, 34:11260–11273.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Continuous doubly constrained batch reinforcement learning.Advances in Neural Information Processing Systems, 34:11260–11273

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.062522Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f82cbb90-947e-4ca4-8a2f-87a56eeb337a · outbound

This paper cites Deep reinforcement learning that matters.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Deep reinforcement learning that matters

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.071370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f49c6e4b-aa79-4c2f-b54f-b06aa19579ff · outbound

This paper cites Batch size-invariance for policy optimization.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Batch size-invariance for policy optimization

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.091633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation acce5128-763f-4f8d-a388-c8df6444d004 · outbound

This paper cites The 37 implementation details of proximal policy optimization.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training The 37 implementation details of proximal policy optimization

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.141074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5ef1f5c4-d947-4f09-90d8-4824bbca8958 · outbound

This paper cites A note on importance sampling using standardized weights.Technical Report 348.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training A note on importance sampling using standardized weights.Technical Report 348

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.017058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4182725d-9c30-4766-b8dc-ffa9773b8dd5 · outbound

This paper cites Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:42:21.047235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 892412d3-78f1-4e34-9199-afed08f9ee8f · outbound

This paper cites Budgeting counterfactual for offline rl.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Budgeting counterfactual for offline rl

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.021166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bd61730b-01e7-4b40-9f0c-17346b1a7ac7 · outbound

This paper cites Deepscaler: Surpassing o1-preview with a 1.5b model by scaling rl.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Deepscaler: Surpassing o1-preview with a 1.5b model by scaling rl

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.033251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2a947907-4c24-4181-99e3-13b8c5a89aa2 · outbound

This paper cites Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:42:21.043232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6cda9dfa-5239-4d64-86d4-d5c33b221210 · outbound

This paper cites 2023 american mathematics competitions (amc 10 and amc 12).

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training 2023 american mathematics competitions (amc 10 and amc 12)

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.037920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation dd2b72ee-884a-4499-a9a6-18ca007fddd7 · outbound

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

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Training language models to follow instructions with human feedback

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:42:21.051093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6eea29ba-3c0e-4598-80c5-2a268297c87a · outbound

This paper cites Defeating the training-inference mismatch via fp16.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Defeating the training-inference mismatch via fp16

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:42:21.009935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 099a9314-ec89-4b4f-a306-e420fdf99257 · outbound

This paper cites Springer Science & Business Media.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Springer Science & Business Media

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.008314Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b8f8f53a-2266-4d34-a9f7-bc115d662516 · outbound

This paper cites Trust region policy optimization.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Trust region policy optimization

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.095829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2d472ba1-ecd6-41c2-8d3e-5a5fd4ed2db4 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Proximal Policy Optimization Algorithms

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:42:21.038720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2326cc52-513c-49e3-8af6-e7a2870fd943 · outbound

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

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:42:21.030358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation be00e02d-b485-48a2-844d-3c8bd9006959 · outbound

This paper cites Ziegler, Ryan Lowe, Chelsea V oss, Alec Radford, Dario Amodei, and Paul Christiano.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Ziegler, Ryan Lowe, Chelsea V oss, Alec Radford, Dario Amodei, and Paul Christiano

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.012612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b495a167-96d8-4f6b-bae2-077b10a8bf82 · outbound

This paper cites Sutton and Andrew G.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Sutton and Andrew G

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.087800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 83357d86-8e76-47b8-8529-4baf4de39174 · outbound

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

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Qwen2.5: A party of foundation models, September 2024

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.029351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 37a9a01a-18e1-46b6-a354-933ded269136 · outbound

This paper cites Qwen3 technical report.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Qwen3 technical report

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.118278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ec249c40-fe0a-42c7-b01a-5129ba583d0a · outbound

This paper cites Fp8 quantization — vllm documentation.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Fp8 quantization — vllm documentation

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.121978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 63f70013-7a03-4d88-85cf-34bce9076dca · outbound

This paper cites Williams.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Williams

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.133369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 892475b6-3b25-4c68-a834-ba959471bee0 · outbound

This paper cites Jet-rl: Enabling on-policy fp8 reinforcement learning with unified training and rollout precision flow.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Jet-rl: Enabling on-policy fp8 reinforcement learning with unified training and rollout precision flow

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.114332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c50ed725-5222-48e1-a881-d227efddd534 · outbound

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

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:42:21.035003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b9b6840d-02a1-4000-9d8f-5a2c899b8ae3 · outbound

This paper cites American invitational mathematics examination (aime) 2024.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training American invitational mathematics examination (aime) 2024

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.137116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f952669a-9237-4939-9ad7-4ea5e9e98524 · outbound

This paper cites American invitational mathematics examination (aime) 2025.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training American invitational mathematics examination (aime) 2025

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.103092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d9e4ca4a-4bd6-45c6-a842-346f026050b8 · outbound

This paper cites American invitational mathematics examination (aime) 2026.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training American invitational mathematics examination (aime) 2026

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T10:17:39.110087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f6945279-67c8-4ce3-abce-d53b6aa41c7a · outbound

This paper cites Group Sequence Policy Optimization.

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Group Sequence Policy Optimization

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:42:21.025655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cb8982e8-5366-41c5-9355-71f1628fd6e5 · outbound

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

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training Fine-Tuning Language Models from Human Preferences

Reference 39

Resolution: metadata mismatch; local_arxiv, observed 2026-05-13T05:42:21.020354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

No inbound Pith citation observations are available.