Paper Citation Record · LEDGER

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training

As of 22 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 1 inbound Pith citation observation for arXiv:2606.04272.

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

pith.paper-citation-record.v1
2606.04272 v1

Coverage vector

measured 51 of 51 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-28T10:37:53.152370Z

measured 52 of 52 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T21:26:33.858637Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

51 of 51 outbound references displayed

verified exact7
verified fuzzy0
unresolved37
parse uncertain0
malformed identifier0
metadata mismatch7

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c50e5123-6655-4a91-909c-42f8823b2885 · outbound

This paper cites Reinforcement learning on pre-training data.arXiv preprint arXiv:2509.19249.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training Reinforcement learning on pre-training data.arXiv preprint arXiv:2509.19249

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:46:29.028151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4383ca90-3c58-411b-a610-ad941016c0a5 · outbound

This paper cites 2026 , url =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training 2026 , url =

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba6d57a6-4722-4e50-a417-4552047a6fb5 · outbound

This paper cites Reinforcement Pre-Training.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training Reinforcement Pre-Training

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:46:29.032828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ca0cfcdb-d01f-40f2-93f1-4ab0139559b1 · outbound

This paper cites Advances in Neural Information Processing Systems , volume =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training Advances in Neural Information Processing Systems , volume =

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a28dced6-e67a-4efa-a83c-a474f8a32073 · outbound

This paper cites an unresolved cited work.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7982491a-0431-440e-a9d2-9b0e517a6f18 · outbound

This paper cites International Conference on Machine Learning (ICML) , pages =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training International Conference on Machine Learning (ICML) , pages =

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5283c9e-cc67-45b0-b767-d4500200055a · outbound

This paper cites Advances in Neural Information Processing Systems , volume =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training Advances in Neural Information Processing Systems , volume =

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb40cfcb-cb99-4967-875d-99f831075796 · outbound

This paper cites Secrets of.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training Secrets of

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6e9194c-8070-4ce0-8925-91144a9be7aa · outbound

This paper cites 2024 , url =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training 2024 , url =

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20e26056-393f-43ec-b02f-ee0fecee4344 · outbound

This paper cites On the Interplay of Pre-Training, Mid-Training, and.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training On the Interplay of Pre-Training, Mid-Training, and

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aed3fbaa-6ff7-406f-a60d-e470c49527ca · outbound

This paper cites arXiv preprint arXiv:2510.15020 , year=.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training arXiv preprint arXiv:2510.15020 , year=

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:46:29.010483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 121a3219-5509-4dcb-8413-376fa84b50a1 · outbound

This paper cites Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:46:29.015086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation bc25554b-1c10-40a0-8f70-03b0c2821027 · outbound

This paper cites 2026 , url =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training 2026 , url =

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8aaedb04-4fc7-4dfb-83eb-95d393d6bef6 · outbound

This paper cites 2025 , url =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training 2025 , url =

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dddd8ad2-1cf7-4d2e-858e-a42cbad3a3e9 · outbound

This paper cites 2023 , organization =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training 2023 , organization =

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c625d6f-91c0-4344-932a-ec98327e595a · outbound

This paper cites Conference on Language Modeling (COLM) , year =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training Conference on Language Modeling (COLM) , year =

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8dcf0d89-f4f1-4bd9-afbf-aa2501561406 · outbound

This paper cites 2024 , url =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training 2024 , url =

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef484a2d-e6c3-430b-8d7b-36e01b57746a · outbound

This paper cites 2024 , url =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training 2024 , url =

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c3a323d-dcc1-422a-9e8f-690dbd1ff8aa · outbound

This paper cites International Conference on Learning Representations (ICLR) , year =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training International Conference on Learning Representations (ICLR) , year =

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 458c0839-00bf-4f33-bb69-c71c4583681e · outbound

This paper cites 2021 , url =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training 2021 , url =

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44f43cd7-81e3-4636-ad1b-e2a264d52ca3 · outbound

This paper cites 2020 , url =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training 2020 , url =

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74d714f0-b551-408f-b3c5-f57ad6dff0cc · outbound

This paper cites Advances in Neural Information Processing Systems , pages =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training Advances in Neural Information Processing Systems , pages =

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46eafb37-2a1a-4896-bd5c-f3a838eb87cd · outbound

This paper cites 2019 , eprint =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training 2019 , eprint =

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2da44d80-0f2b-40c8-9865-e1fb13575ba5 · outbound

This paper cites 2024 , url =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training 2024 , url =

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08fb571e-44b2-4a4b-ac05-09818c4d67c9 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training Evaluating Large Language Models Trained on Code

Reference 25

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T02:46:29.005163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 070a267f-bb99-4b75-8997-9cbec284a564 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training Training Verifiers to Solve Math Word Problems

Reference 26

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T02:46:29.000903Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 76901fb7-a0f7-4e7d-b8e5-331645346cce · outbound

This paper cites Measuring Mathematical Problem Solving with the.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training Measuring Mathematical Problem Solving with the

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d879b86-e998-44ce-9933-a219600d4a5b · outbound

This paper cites Does Reinforcement Learning Really Incentivize Reasoning Capacity in.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training Does Reinforcement Learning Really Incentivize Reasoning Capacity in

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48876333-6ea8-4b76-9383-9b5c824b7b12 · outbound

This paper cites Training Compute-Optimal Large Language Models.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training Training Compute-Optimal Large Language Models

Reference 29

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T02:46:29.019630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation df50f29f-2842-4f13-b1c0-130c4a385d85 · outbound

This paper cites The Invisible Leash: Why.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training The Invisible Leash: Why

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d37cba8-1c47-487c-ab06-85da1c859b13 · outbound

This paper cites 2023 , url =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training 2023 , url =

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a3f247f-3421-45dd-8857-e1b8b5637a01 · outbound

This paper cites 2025 , url =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training 2025 , url =

Reference 32

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 105465d2-7129-4f7d-bb0e-caeb01e29c86 · outbound

This paper cites Olmo 3.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training Olmo 3

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:46:29.023535Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5728a67e-fc49-43da-bdbf-369bcfcf5586 · outbound

This paper cites Learning to Reason under Off-Policy Guidance.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training Learning to Reason under Off-Policy Guidance

Reference 34

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T02:46:28.991589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 336a2e91-d373-4b2f-9122-4a4757173a7e · outbound

This paper cites 2026 , url =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training 2026 , url =

Reference 35

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02792363-90c7-4c3d-8015-dfe1491fb7e3 · outbound

This paper cites 2025 , url =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training 2025 , url =

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a645d370-9dcd-4c3a-ab77-486656631ffb · outbound

This paper cites International Conference on Machine Learning (ICML) , year =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training International Conference on Machine Learning (ICML) , year =

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 540bccad-7215-41fb-853e-e5f01f4aadf3 · outbound

This paper cites Towards a unified view of large language model post-training.arXiv preprint arXiv:2509.04419.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training Towards a unified view of large language model post-training.arXiv preprint arXiv:2509.04419

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:46:28.998009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7804ce0a-a8ac-4ce4-8ba0-18495b214c2a · outbound

This paper cites 2025 , url =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training 2025 , url =

Reference 39

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a052105-5b53-4020-a542-742571cee4f4 · outbound

This paper cites arXiv preprint arXiv:2508.11408 , year=.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training arXiv preprint arXiv:2508.11408 , year=

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:46:28.984570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0b6ae605-f2f8-44b8-91c1-46d0617c85a8 · outbound

This paper cites Reasoning with Sampling: Your Base Model is Smarter Than You Think.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training Reasoning with Sampling: Your Base Model is Smarter Than You Think

Reference 41

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T02:46:28.988369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a0a1b4ef-e6b4-48a5-a829-75a391b07927 · outbound

This paper cites 2025 , url =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training 2025 , url =

Reference 42

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e199826d-5b70-4d5a-ba19-84ea89c70b74 · outbound

This paper cites 2025 , url =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training 2025 , url =

Reference 43

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b23aab82-b223-4a18-9989-2398ff665ae0 · outbound

This paper cites Proceedings of the National Academy of Sciences , volume =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training Proceedings of the National Academy of Sciences , volume =

Reference 44

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 673226cb-ef8f-4a45-8026-8d9c8c439844 · outbound

This paper cites 2026 , url =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training 2026 , url =

Reference 45

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c4ea56d-bbe6-4ac9-ac4f-f2239273c100 · outbound

This paper cites 2024 , url =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training 2024 , url =

Reference 46

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9eba6ef1-07e6-40bc-bdbe-0a3752181737 · outbound

This paper cites 2025 , url =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training 2025 , url =

Reference 47

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d40eddb5-23b1-42d0-9853-690827aeed2a · outbound

This paper cites The Art of Scaling Reinforcement Learning Compute for LLMs.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training The Art of Scaling Reinforcement Learning Compute for LLMs

Reference 48

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T02:46:28.994858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e6b48ae6-c1de-452f-9bb0-097b29c260aa · outbound

This paper cites 2025 , eprint=.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training 2025 , eprint=

Reference 49

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64043b4a-9574-4f4e-b31e-51a8bbbe24ae · outbound

This paper cites 2026 , eprint=.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training 2026 , eprint=

Reference 50

Resolution: unresolved; no resolver link, observed 2026-06-28T10:37:53.152370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da46f109-766e-4bfe-9bb9-aef13c358ebd · outbound

This paper cites arXiv preprint arXiv:2412.04619 , year =.

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training arXiv preprint arXiv:2412.04619 , year =

Reference 51

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T02:46:28.980781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Pith citing papers

Observation 9a5d67da-066c-4e9a-9def-35c2a8f57ba4 · inbound

Understanding Reasoning from Pretraining to Post-Training cites this paper.

Understanding Reasoning from Pretraining to Post-Training RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T21:26:33.858637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.