Paper Citation Record · LEDGER

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs

As of 6 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2606.17735.

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

pith.paper-citation-record.v1
2606.17735 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-27T00:48:56.892634Z

measured 37 of 37 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

37 of 37 outbound references displayed

verified exact32
verified fuzzy0
unresolved2
parse uncertain0
malformed identifier0
metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bb33b206-c858-4eb3-88ed-e13ab3645cda · outbound

This paper cites Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-07-03T21:08:58.849123Z

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 d5faa1f9-4e02-4910-85cd-3fda3b150e26 · outbound

This paper cites A Survey of Reinforcement Learning for Large Reasoning Models.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs A Survey of Reinforcement Learning for Large Reasoning Models

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-03T21:08:58.861020Z

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 ca03c586-95e5-467b-a080-52bc8ff08e3b · outbound

This paper cites Reinforcement Learning for Long-Horizon Interactive LLM Agents.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs Reinforcement Learning for Long-Horizon Interactive LLM Agents

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-07-03T21:18:58.371419Z

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 c52240c1-8467-4371-9340-c9db88b9fb3a · outbound

This paper cites ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-07-03T21:18:58.398809Z

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 60250b10-1048-4cf3-a447-b61dc719b8d5 · outbound

This paper cites Large language model reasoning failures.arXiv preprint arXiv:2602.06176.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs Large language model reasoning failures.arXiv preprint arXiv:2602.06176

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T21:18:58.374020Z

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 10196b18-3880-4df7-a95e-e48a0fa945f5 · outbound

This paper cites arXiv preprint arXiv:2602.01288 , year=.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs arXiv preprint arXiv:2602.01288 , year=

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-03T21:18:58.392439Z

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 ce81ecab-1249-4d57-ba80-818dd8c6825b · outbound

This paper cites Reasoning Can Be Restored by Correcting a Few Decision Tokens.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs Reasoning Can Be Restored by Correcting a Few Decision Tokens

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-07-03T21:18:58.340911Z

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 4bf21333-ba45-47d0-8aa3-d524641dcc6a · outbound

This paper cites YuLan: An Open-source Large Language Model.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs YuLan: An Open-source Large Language Model

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-07-03T21:18:58.386862Z

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 3e9b128a-5262-44cf-a893-034adde9778d · outbound

This paper cites org/abs/2603.16790.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs org/abs/2603.16790

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T21:18:58.383757Z

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 5eb652c5-a99a-4dd6-8538-e5b53434f88c · outbound

This paper cites Iquest-coder-v1 technical report.arXiv preprint arXiv:2603.16733, 2026b.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs Iquest-coder-v1 technical report.arXiv preprint arXiv:2603.16733, 2026b

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-07-03T21:18:58.384774Z

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 ea62d952-3925-4f51-9dc8-d2fe78c4813d · outbound

This paper cites A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-07-03T21:18:58.377454Z

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 f13d3bd3-8636-49bf-9f23-ca2825a91b1d · outbound

This paper cites Reward under attack: Analyzing the robustness and hackability of process reward models.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs Reward under attack: Analyzing the robustness and hackability of process reward models

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-07-03T21:18:58.359171Z

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 9aac31a8-6bc2-4a4a-a4b0-ac0388280c0b · outbound

This paper cites Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-07-03T21:18:58.372138Z

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 fca526ff-4e66-4cca-8a5d-6cc9e535664d · outbound

This paper cites More test-time compute can hurt: Overestimation bias in llm beam search.arXiv preprint arXiv:2603.15377,.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs More test-time compute can hurt: Overestimation bias in llm beam search.arXiv preprint arXiv:2603.15377,

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-07-03T21:18:58.402092Z

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 4dd49caf-9621-40ee-ad3f-5fe8b710e869 · outbound

This paper cites From Curiosity to Caution: Mitigating Reward Hacking for Best-of-N with Pessimism.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs From Curiosity to Caution: Mitigating Reward Hacking for Best-of-N with Pessimism

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-07-03T21:18:58.404824Z

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 b1a72380-ad28-4828-af6e-72db290a8683 · outbound

This paper cites Junbo Li, Peng Zhou, Rui Meng, Meet P.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs Junbo Li, Peng Zhou, Rui Meng, Meet P

Reference 16

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T21:18:58.333883Z

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 47791efb-a617-49b5-bc38-87f1fdeec26e · outbound

This paper cites Int: Self-proposed interventions enable credit assignment in llm reasoning.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs Int: Self-proposed interventions enable credit assignment in llm reasoning

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-07-03T21:18:58.387573Z

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 c7fe5dad-8229-4c64-84c9-62bd1b7988c1 · outbound

This paper cites Adaptive KV Cache Reuse for Fast Long-Context LLM Serving.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs Adaptive KV Cache Reuse for Fast Long-Context LLM Serving

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-07-03T21:18:58.407427Z

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 aa43bd65-83b7-400c-83d7-429dca86b6c5 · outbound

This paper cites ArborKV: Structure-Aware KV Cache Management for Scaling Tree-based LLM Reasoning.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs ArborKV: Structure-Aware KV Cache Management for Scaling Tree-based LLM Reasoning

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-07-03T21:08:58.857588Z

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 3315d004-c551-43b2-9254-19e8a79e0799 · outbound

This paper cites Qwen3 Technical Report.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs Qwen3 Technical Report

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-07-03T21:18:58.389583Z

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 b09bb816-eef6-443a-bba6-cee66ed2240f · outbound

This paper cites Closed-loop transformers: Autoregressive modeling as iterative latent equilibrium.arXiv preprint arXiv:2511.21882,.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs Closed-loop transformers: Autoregressive modeling as iterative latent equilibrium.arXiv preprint arXiv:2511.21882,

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-07-03T21:18:58.379863Z

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 2369deb1-4c14-4f6b-8905-f0fb3c79a0bd · outbound

This paper cites Mmrpt: Multimodal reinforcement pre-training via masked vision-dependent reasoning.arXiv preprint arXiv:2512.07203, 2025c.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs Mmrpt: Multimodal reinforcement pre-training via masked vision-dependent reasoning.arXiv preprint arXiv:2512.07203, 2025c

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-07-03T21:18:58.380481Z

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 70e36fa2-6a44-4fcb-8375-76f2025b988d · outbound

This paper cites arXiv preprint arXiv:2603.09065 , year=.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs arXiv preprint arXiv:2603.09065 , year=

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-07-03T21:18:58.356277Z

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 82e3a9ec-f72b-42da-b747-44ef9f62ab08 · outbound

This paper cites AAPA: Adversarially Anchored Preference Alignment for Post-Training of Large Language Models.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs AAPA: Adversarially Anchored Preference Alignment for Post-Training of Large Language Models

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-07-03T21:18:58.374761Z

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 4e5c98fd-1684-4b7a-b208-b492eb431894 · outbound

This paper cites Early Decisions Matter: Proximity Bias and Initial Trajectory Shaping in Non-Autoregressive Diffusion Language Models.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs Early Decisions Matter: Proximity Bias and Initial Trajectory Shaping in Non-Autoregressive Diffusion Language Models

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-07-03T21:18:58.395252Z

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 8ddeb62a-f527-43c7-b8ce-79a8a1b90ca1 · outbound

This paper cites Corefine: Confidence-guided self-refinement for adaptive test-time compute.arXiv preprint arXiv:2602.08948, 2026a.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs Corefine: Confidence-guided self-refinement for adaptive test-time compute.arXiv preprint arXiv:2602.08948, 2026a

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-07-03T21:18:58.392569Z

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 fa684804-bab1-498f-a8d2-6b28a0d03fa7 · outbound

This paper cites Understanding reasoning in thinking language models via steering vectors.arXiv preprint arXiv:2506.18167.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs Understanding reasoning in thinking language models via steering vectors.arXiv preprint arXiv:2506.18167

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-07-03T21:18:58.353528Z

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 a84dbcc5-af56-4be8-99a1-7aa055112616 · outbound

This paper cites PILOT: Planning via Internalized Latent Optimization Trajectories for Large Language Models.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs PILOT: Planning via Internalized Latent Optimization Trajectories for Large Language Models

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-07-03T21:18:58.382207Z

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 00686bbf-8d21-4b3c-9757-0d3be16d8793 · outbound

This paper cites HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agents.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agents

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-07-03T21:18:58.338366Z

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 fc57e249-3b1a-4fa1-828e-a015484f138d · outbound

This paper cites Probabilistic soundness guarantees in llm reasoning chains.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs Probabilistic soundness guarantees in llm reasoning chains

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-27T00:48:56.892634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89b0f538-d471-446b-ba6b-a47cfcb5424d · outbound

This paper cites Prism: Pushing the frontier of deep think via process reward model-guided inference.arXiv preprint arXiv:2603.02479,.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs Prism: Pushing the frontier of deep think via process reward model-guided inference.arXiv preprint arXiv:2603.02479,

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-07-03T21:18:58.359524Z

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 65c61e8d-c18c-4ffd-94d5-6f94025a9aec · outbound

This paper cites v 1: Unifying generation and self-verification for parallel reasoners.arXiv preprint arXiv:2603.04304, 2026a.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs v 1: Unifying generation and self-verification for parallel reasoners.arXiv preprint arXiv:2603.04304, 2026a

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-07-03T21:18:58.366082Z

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 365dd4e4-44fb-4a6a-980e-69e8631d0689 · outbound

This paper cites DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-07-03T21:18:58.389882Z

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 10591c9e-6fd0-420f-a861-07e92f28ec32 · outbound

This paper cites Group Sequence Policy Optimization.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs Group Sequence Policy Optimization

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-07-03T21:08:58.863995Z

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 8124e925-d29c-4936-a827-8f80984bd642 · outbound

This paper cites Disco: Re- inforcing large reasoning models with discriminative con- strained optimization.arXiv preprint arXiv:2505.12366.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs Disco: Re- inforcing large reasoning models with discriminative con- strained optimization.arXiv preprint arXiv:2505.12366

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-07-03T21:08:58.868789Z

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 24d57e2e-a177-4eea-86b4-6178b2760c23 · outbound

This paper cites The proposed method does not involve human subjects, private user data, or personally identifiable information.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs The proposed method does not involve human subjects, private user data, or personally identifiable information

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-27T00:48:56.892634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c5c2945-2225-4fb8-a332-9faebfa4a26b · outbound

This paper cites an unresolved cited work.

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs Unresolved cited work

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-07-03T21:08:58.871510Z

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.

Pith citing papers

No inbound Pith citation observations are available.