Paper Citation Record · LEDGER

Predictive Divergence Masks for LLM RL

As of 9 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 0 inbound Pith citation observations for arXiv:2607.10848.

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

pith.paper-citation-record.v1
2607.10848 v1

Coverage vector

measured 27 of 27 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-14T08:49:37.615924Z

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

27 of 27 outbound references displayed

verified exact0
verified fuzzy0
unresolved27
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 68551c4e-dc65-4aed-bdb1-f151fabf8187 · outbound

This paper cites Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs.

Predictive Divergence Masks for LLM RL Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52ac8a75-1c16-4bfe-a1ca-1fa17084e47c · outbound

This paper cites MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention.

Predictive Divergence Masks for LLM RL MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 906cac7a-da9c-4681-b459-2d42a2f87604 · outbound

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

Predictive Divergence Masks for LLM RL DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6deee50-f3d8-42a3-8e35-22a2bb1d132e · outbound

This paper cites https://thinkingmachines.ai/blog/defeating-nondeterminism-in- llm-inference/.

Predictive Divergence Masks for LLM RL https://thinkingmachines.ai/blog/defeating-nondeterminism-in- llm-inference/

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6c6f435-b655-48f1-9fec-eb2b48ee8b53 · outbound

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

Predictive Divergence Masks for LLM RL Understanding R1-Zero-Like Training: A Critical Perspective

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0eb8cef3-6fd1-42ae-b224-2feaf23564c4 · outbound

This paper cites Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning.

Predictive Divergence Masks for LLM RL Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70c6814d-7b83-431a-8c00-a43aeddf6ae4 · outbound

This paper cites Defeating the training-inference mismatch via fp16.arXiv preprint arXiv:2510.26788,.

Predictive Divergence Masks for LLM RL Defeating the training-inference mismatch via fp16.arXiv preprint arXiv:2510.26788,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0215ada-3e65-4c29-8cd0-763b780cc13d · outbound

This paper cites Rethinking the Trust Region in LLM Reinforcement Learning.

Predictive Divergence Masks for LLM RL Rethinking the Trust Region in LLM Reinforcement Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a31a58da-a056-41e9-8ed3-7d959e170055 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Predictive Divergence Masks for LLM RL Proximal Policy Optimization Algorithms

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b62590e-aeb5-47dc-8912-7f00e983fdd1 · outbound

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

Predictive Divergence Masks for LLM RL DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5423e8eb-5d03-4520-bb39-c284be433c82 · outbound

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

Predictive Divergence Masks for LLM RL HybridFlow: A Flexible and Efficient RLHF Framework

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fa69b9c-a5e3-4df8-9ea9-5222a7380d00 · outbound

This paper cites Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism.

Predictive Divergence Masks for LLM RL Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d28266e3-e8ba-4885-91e6-b672dc761455 · outbound

This paper cites Kimi k1.5: Scaling Reinforcement Learning with LLMs.

Predictive Divergence Masks for LLM RL Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff94ef2b-28cd-49bc-9af9-e63f2b4be31b · outbound

This paper cites Simple Policy Optimization.

Predictive Divergence Masks for LLM RL Simple Policy Optimization

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45e72984-97cd-420a-8b54-9113b30ba513 · outbound

This paper cites Qwen3 Technical Report.

Predictive Divergence Masks for LLM RL Qwen3 Technical Report

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5861436c-563c-4e29-9d3e-c224264a6331 · outbound

This paper cites Rethinking the Divergence Regularization in LLM RL.

Predictive Divergence Masks for LLM RL Rethinking the Divergence Regularization in LLM RL

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 335fd98d-8447-453d-adf1-5664ee146f3d · outbound

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

Predictive Divergence Masks for LLM RL DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a80c74fc-c51f-4766-a16c-9c8c9ee4f54c · outbound

This paper cites Stabilizing reinforcement learning with llms: Formulation and practices.arXiv preprint arXiv:2512.01374,.

Predictive Divergence Masks for LLM RL Stabilizing reinforcement learning with llms: Formulation and practices.arXiv preprint arXiv:2512.01374,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c040be7-4644-4a71-ad7a-08c77ae88e6e · outbound

This paper cites Reinforcing General Reasoning without Verifiers.

Predictive Divergence Masks for LLM RL Reinforcing General Reasoning without Verifiers

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d701038e-e666-4992-8d4a-dd92dcb8800c · outbound

This paper cites an unresolved cited work.

Predictive Divergence Masks for LLM RL Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 722c673d-87a4-41cb-9887-8a4da861ba9a · outbound

This paper cites GRPO (Shao et al.,.

Predictive Divergence Masks for LLM RL GRPO (Shao et al.,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cfebd66-a1dd-4f1a-b6ab-4a7422b3d5ea · outbound

This paper cites an unresolved cited work.

Predictive Divergence Masks for LLM RL Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dd4f3d8-062a-4429-92f4-e9cca86232e2 · outbound

This paper cites These methods modify the objective or the clipping rule, but they still decide the update direction from the sampled importance ratio.

Predictive Divergence Masks for LLM RL These methods modify the objective or the clipping rule, but they still decide the update direction from the sampled importance ratio

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bb1750d-f617-4116-8345-fc7dadec84cf · outbound

This paper cites (5) that we build on.

Predictive Divergence Masks for LLM RL (5) that we build on

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38072ebf-d0b6-44c5-bc05-9d4b3b38beb3 · outbound

This paper cites Aggregated-tail estimator.Under the top-K aggregated-tail construction, the support contains the retained tokensK and one tail bucket.

Predictive Divergence Masks for LLM RL Aggregated-tail estimator.Under the top-K aggregated-tail construction, the support contains the retained tokensK and one tail bucket

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ee75953-0c84-48f1-b679-d164f04cf47b · outbound

This paper cites By default, both training and rollout use BF16.

Predictive Divergence Masks for LLM RL By default, both training and rollout use BF16

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6836379-670c-4122-b8d1-2462534f9de2 · outbound

This paper cites an unresolved cited work.

Predictive Divergence Masks for LLM RL Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-14T08:49:37.615924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.