Paper Citation Record · LEDGER

Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners

As of 7 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2606.29296.

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

pith.paper-citation-record.v1
2606.29296 v1

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-30T07:33:55.284758Z

measured 18 of 18 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+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

18 of 18 outbound references displayed

verified exact6
verified fuzzy0
unresolved2
parse uncertain0
malformed identifier1
metadata mismatch9

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4bd02a22-1010-4a61-a1af-0e9881eb6641 · outbound

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

Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:34:21.180773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1cdd8a9e-171f-450b-9f4f-b7a2e0a06c6c · outbound

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

Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T07:34:20.679568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a2104129-86f3-4840-ba2f-df6f312ef891 · outbound

This paper cites Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training.

Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:34:21.178202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 61182028-d306-4652-8739-f1b2efda3b50 · outbound

This paper cites From Reasoning to Agentic: Credit Assignment in Reinforcement Learning for Large Language Models.

Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners From Reasoning to Agentic: Credit Assignment in Reinforcement Learning for Large Language Models

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:34:21.175163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b5141abb-d49c-4149-a2f3-10b441144e9d · outbound

This paper cites Tackling Length Inflation Without Trade-offs: Group Relative Reward Rescaling.

Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners Tackling Length Inflation Without Trade-offs: Group Relative Reward Rescaling

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-06-30T07:34:21.201958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9121599e-67e2-4b46-b717-87f431398145 · outbound

This paper cites Fipo: Eliciting deep reasoning with future-kl influenced policy optimization.

Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners Fipo: Eliciting deep reasoning with future-kl influenced policy optimization

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T07:34:21.183878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2089c9ec-877d-485d-a7de-9a276d833b30 · outbound

This paper cites Junxi Yin, Haisen Luo, Zhenyu Li, Yihua Liu, Dan Liu, Zequn Li, and Xiaohang Xu.

Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners Junxi Yin, Haisen Luo, Zhenyu Li, Yihua Liu, Dan Liu, Zequn Li, and Xiaohang Xu

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-06-30T07:34:21.208021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d0a1ea47-ae02-4361-a8f3-bb93f2e628c7 · outbound

This paper cites Pinpointing crucial steps: Attribution-based credit assignment for verifiable reinforcement learning.arXiv preprint arXiv:2510.08899.

Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners Pinpointing crucial steps: Attribution-based credit assignment for verifiable reinforcement learning.arXiv preprint arXiv:2510.08899

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T07:34:21.198548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c43312f5-f21f-47e1-9ba6-50aae585c62f · outbound

This paper cites Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment.

Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment

Reference 9

Resolution: malformed identifier; doi_truncated, observed 2026-06-30T07:34:20.679855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d9a15bad-183c-43fa-90d7-579b34f4bb28 · outbound

This paper cites Drpo: Efficient reasoning via decoupled reward policy optimization.

Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners Drpo: Efficient reasoning via decoupled reward policy optimization

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T07:34:21.205151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 164d8e26-45ef-4cf3-8df2-4949f61a554c · outbound

This paper cites Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey.

Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-08-04T02:39:30.770950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 21ccff55-542f-47bb-8b8e-6372587e1828 · outbound

This paper cites Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation.

Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation

Reference 12

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T07:34:21.186840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5c210f49-f540-4104-a341-0d2b6abc61a3 · outbound

This paper cites Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement.

Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-06-30T07:34:21.192165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6311e93f-6bf9-4425-b939-c5455ad5fd4c · outbound

This paper cites an unresolved cited work.

Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-30T07:33:55.284758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f91f9df-6b75-48ce-a74c-fe82f04854bc · outbound

This paper cites Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps.

Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps

Reference 15

Resolution: metadata mismatch; doi, observed 2026-06-30T07:34:20.683703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation af4dd9d7-5f6a-49ad-963d-d50f7f2a66b5 · outbound

This paper cites ♫ M u S i Q ue: Multihop Questions via Single-hop Question Composition.

Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners ♫ M u S i Q ue: Multihop Questions via Single-hop Question Composition

Reference 16

Resolution: metadata mismatch; doi, observed 2026-06-30T07:34:20.689750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 98ac186d-3007-4402-a640-ff7c727d445f · outbound

This paper cites Qwen2.5 Technical Report.

Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners Qwen2.5 Technical Report

Reference 17

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T07:34:21.189518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 35ecaa5c-aadf-4b27-a957-aff9c423f466 · outbound

This paper cites Setting k<1.0 protects necessary reasoning verbosity and raises the exploratory ceiling; k=0.7 achieves the best average pass@1 and is used as the default throughout this paper.

Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners Setting k<1.0 protects necessary reasoning verbosity and raises the exploratory ceiling; k=0.7 achieves the best average pass@1 and is used as the default throughout this paper

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-30T07:33:55.284758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.