Paper Citation Record · LEDGER

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning

As of 11 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2604.14922.

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

pith.paper-citation-record.v1
2604.14922 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T11:17:43.769244Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+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

38 of 38 outbound references displayed

verified exact26
verified fuzzy2
unresolved10
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d322676a-88e3-494d-809b-67839910637a · outbound

This paper cites an unresolved cited work.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-05-19T14:47:36.910641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation c3eeca08-faf1-4a77-942d-2993c8b387e0 · outbound

This paper cites an unresolved cited work.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-05-19T14:47:36.914843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 9a7d95af-e313-4fab-954f-d3e777968acc · outbound

This paper cites an unresolved cited work.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-05-19T14:47:36.916952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 74357d40-37d4-45c9-8ea4-18d4cfd6773b · outbound

This paper cites Round and Round We Go! What makes Rotary Positional Encodings useful?.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning Round and Round We Go! What makes Rotary Positional Encodings useful?

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-10T11:20:10.548528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 03a41d8f-7ba1-467d-97bd-0be879ceab3b · outbound

This paper cites The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-12T12:31:34.026635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e3d4c4ac-5b78-400e-9000-abfed01d31b8 · outbound

This paper cites Fan, Y ., He, X., Yang, D., Zheng, K., Kuo, C.-C., Zheng, Y ., Narayanaraju, S.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning Fan, Y ., He, X., Yang, D., Zheng, K., Kuo, C.-C., Zheng, Y ., Narayanaraju, S

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-10T11:20:10.558602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 507adf49-74c0-4538-8fee-34c7584ae138 · outbound

This paper cites an unresolved cited work.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-05-19T14:47:36.912819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ef106555-7364-40de-ace9-cd441cde02c4 · outbound

This paper cites Unlocking Continual Learning Abilities in Language Models.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning Unlocking Continual Learning Abilities in Language Models

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-10T11:20:10.563055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 3772f3b3-2b63-4da8-a594-fef652386ee2 · outbound

This paper cites SeerAttention-R: Sparse Attention Adaptation for Long Reasoning.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning SeerAttention-R: Sparse Attention Adaptation for Long Reasoning

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-10T11:20:10.553722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 7fbbe937-8222-4034-8e5a-29acc58613c5 · outbound

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

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-10T11:20:10.493377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 3cf4f915-e0c0-4841-b2c1-d644b29341ab · outbound

This paper cites Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-10T11:20:10.524206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 59b6fea0-fec8-4801-a4ef-2dfbe023cd93 · outbound

This paper cites Training Large Language Models to Reason in a Continuous Latent Space.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning Training Large Language Models to Reason in a Continuous Latent Space

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:29:05.896693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 2c522065-4907-43d8-8f0f-618a80b35959 · outbound

This paper cites RULER: What's the Real Context Size of Your Long-Context Language Models?.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning RULER: What's the Real Context Size of Your Long-Context Language Models?

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-11T03:55:20.729537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ce2a5afe-49a6-46a3-85f4-9e4ce24851b3 · outbound

This paper cites DecIF: Improving Instruction-Following through Meta-Decomposition.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning DecIF: Improving Instruction-Following through Meta-Decomposition

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-10T11:20:10.520003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation be338f70-addb-4805-a9ef-1db84a9d396a · outbound

This paper cites Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-10T11:20:10.533330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 8b5c6149-de6a-4534-afff-0e85b0460854 · outbound

This paper cites an unresolved cited work.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-05-19T14:47:36.908874Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 230485aa-0961-4193-b05f-1ba72b06f1b2 · outbound

This paper cites KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:53:12.376678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 7e097cbd-9d9b-4eb1-bb34-89716cd9cebb · outbound

This paper cites an unresolved cited work.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-05-19T14:47:36.905037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 873c2879-b17e-4d9e-a6d8-933c05fd40bd · outbound

This paper cites arXiv preprint arXiv:2602.05758 , year =.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning arXiv preprint arXiv:2602.05758 , year =

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-10T11:20:10.500672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 8f5cf5f5-f248-4d00-b3fe-e2499dce4013 · outbound

This paper cites an unresolved cited work.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-05-19T14:47:36.899745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 9a4e7baf-9c76-40e5-b20b-e994d773feda · outbound

This paper cites an unresolved cited work.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-05-19T14:47:36.897799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 6f8fa986-c4ea-497b-b2db-31995225f0b9 · outbound

This paper cites Equivalence Between Policy Gradients and Soft Q-Learning.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning Equivalence Between Policy Gradients and Soft Q-Learning

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-10T11:20:10.489677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ecf74f66-0ac7-4a8c-b02a-40f41a5700ba · outbound

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

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-10T11:20:10.538300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 9be31655-5259-42f2-993d-1407f4979434 · outbound

This paper cites Kimi K2: Open Agentic Intelligence.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning Kimi K2: Open Agentic Intelligence

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-10T17:49:28.234076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation db989a8b-4eba-46ad-864b-788b1755bb8d · outbound

This paper cites Kimi Linear: An Expressive, Efficient Attention Architecture.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning Kimi Linear: An Expressive, Efficient Attention Architecture

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-13T23:49:11.451207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 09359c09-4f30-4b56-809f-eea5b947814a · outbound

This paper cites MiniCPM4: Ultra-Efficient LLMs on End Devices.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning MiniCPM4: Ultra-Efficient LLMs on End Devices

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-10T11:20:10.528750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 36cfaa94-33ae-4009-9417-ef4af0b4d499 · outbound

This paper cites QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-10T11:20:10.482511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation c3cf7b96-2912-44bc-aeb4-1ee1c9ba6b39 · outbound

This paper cites arXiv preprint arXiv:2510.19363 , year =.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning arXiv preprint arXiv:2510.19363 , year =

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-10T11:20:10.466761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d6f9dbf9-e1a6-40bd-88f6-739715718f76 · outbound

This paper cites an unresolved cited work.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-05-19T14:47:36.896073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 8b2a197d-5def-4226-bee7-33564836cdde · outbound

This paper cites SLMRec: Distilling Large Language Models into Small for Sequential Recommendation.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning SLMRec: Distilling Large Language Models into Small for Sequential Recommendation

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-10T11:20:10.457959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ff3a4f1b-7191-47ba-afd4-97d9f828c050 · outbound

This paper cites MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-15T11:17:24.684684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 3df12db4-4687-4464-8af2-cf286a543339 · outbound

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

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-05-10T11:20:10.485818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 9fe59d9b-51e3-4c12-98a0-21c626bf4ec7 · outbound

This paper cites GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-11T17:50:08.654972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 86860cb8-799a-4b94-b72b-507bba5edf1a · outbound

This paper cites an unresolved cited work.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-05-19T14:47:36.906973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 66215da3-9290-42fe-aca6-f7819ac01065 · outbound

This paper cites Infllm-v2: Dense-sparse switchable attention for seamless short-to-long adaptation.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning Infllm-v2: Dense-sparse switchable attention for seamless short-to-long adaptation

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-10T11:20:10.462207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation af84ba31-b3dc-4647-a1e6-944885528008 · outbound

This paper cites Group Sequence Policy Optimization.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning Group Sequence Policy Optimization

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-10T19:22:54.227899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 1e2d8cdf-e410-4931-bfe6-f7b86701716c · outbound

This paper cites online" 'onlinestring :=.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning online" 'onlinestring :=

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T14:47:36.901836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 23e3823b-8cad-4187-9932-bda3587b3457 · outbound

This paper cites write newline.

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning write newline

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T14:47:36.894027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Pith citing papers

No inbound Pith citation observations are available.