Paper Citation Record · LEDGER

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models

As of 7 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 6 inbound Pith citation observations for arXiv:2505.17697.

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

pith.paper-citation-record.v1
2505.17697 v1

Coverage vector

measured 58 of 58 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:46:19.068265Z

measured 64 of 64 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T16:46:01.206824Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

58 of 58 outbound references displayed

verified exact1
verified fuzzy7
unresolved50
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 36d688b8-fbc4-4866-b1d6-b43e0f961024 · outbound

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

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:13.105366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 701cc41c-f125-4704-a7bc-2d5fd15515eb · outbound

This paper cites Qwq: Reflect deeply on the boundaries of the unknown.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Qwq: Reflect deeply on the boundaries of the unknown

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:46:21.711879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d9a3552a-6555-442a-8abc-c1ed9e71a78c · outbound

This paper cites OpenAI o1 System Card.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models OpenAI o1 System Card

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:13.321636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9f00f70-0be5-4c96-a0a4-5e869a232ef2 · outbound

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

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:13.429068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf57bf20-1cae-4bb9-bec5-79632e29f28a · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Chain-of-thought prompting elicits reasoning in large language models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:13.517449Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e35523a1-55af-462e-9760-58367039a88f · outbound

This paper cites RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:13.583355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d59b155b-ab1b-4502-8b9e-7c452f59feca · outbound

This paper cites Demystifying Long Chain-of-Thought Reasoning in LLMs.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Demystifying Long Chain-of-Thought Reasoning in LLMs

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:13.708971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d19e77e3-b165-4f9c-935d-a732ad3f57ad · outbound

This paper cites Distilling System 2 into System 1.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Distilling System 2 into System 1

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:13.808759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6778c7a6-ea67-44ee-9d54-63587336a030 · outbound

This paper cites RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:13.968664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2caefea0-b55d-452a-8080-eaa84af2ac0d · outbound

This paper cites RRHF: Rank Responses to Align Language Models with Human Feedback without tears.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models RRHF: Rank Responses to Align Language Models with Human Feedback without tears

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:14.038195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e98105a-f30d-421a-848d-ea70f25e3e97 · outbound

This paper cites Language Models are Multilingual Chain-of-Thought Reasoners.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Language Models are Multilingual Chain-of-Thought Reasoners

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:14.171691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8f2f4c1-817e-4334-be8b-6206c7404489 · outbound

This paper cites Activation addition: Steering language models without optimization.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Activation addition: Steering language models without optimization

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:14.291241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2781fba5-15c9-4c84-a301-30e30491663f · outbound

This paper cites Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:14.386599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76685b9a-5938-436a-b38b-df1d8f68c71b · outbound

This paper cites Measuring mathematical problem solving with the math dataset.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Measuring mathematical problem solving with the math dataset

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:14.491489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 238c0110-8952-468a-81f8-8b1d5f942611 · outbound

This paper cites Qwen2.5: A party of foundation models, September 2024.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Qwen2.5: A party of foundation models, September 2024

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:14.670460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e5e0c71-5c6d-4352-acfc-10689d82e566 · outbound

This paper cites Overtrained Language Models Are Harder to Fine-Tune.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Overtrained Language Models Are Harder to Fine-Tune

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:14.770089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45c2478c-69d3-497f-aa5a-a2f9123d7010 · outbound

This paper cites Gpqa: A graduate-level google-proof q&a benchmark.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Gpqa: A graduate-level google-proof q&a benchmark

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:14.870601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd34cbf1-6d0f-44d7-ada5-35e0c1095c0b · outbound

This paper cites LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:14.997716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ab3989a-e047-4c12-957f-fa7cb8dbd755 · outbound

This paper cites LIMO: Less is More for Reasoning.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models LIMO: Less is More for Reasoning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:15.092652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d7efaae-f87d-4c6f-a382-ff80d6cabbca · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Evaluating Large Language Models Trained on Code

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:15.191974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f288f5b7-ea06-464d-9600-ba29aff74b18 · outbound

This paper cites Efficient memory management for large language model serving with pagedattention.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Efficient memory management for large language model serving with pagedattention

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:15.315911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab6d0c12-ebd9-439e-8b5a-2901f19f96c6 · outbound

This paper cites GPT-4 Technical Report.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models GPT-4 Technical Report

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:15.448809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18be4a2f-44f8-4893-a669-79215528f10b · outbound

This paper cites The claude 3 model family: Opus, sonnet, haiku.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models The claude 3 model family: Opus, sonnet, haiku

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:46:21.455235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d16fd9b0-42e2-4641-8ce9-02e041e43145 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:15.637146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74687a73-7780-467c-b8bb-ba7342c4fe3d · outbound

This paper cites Qwen3 Technical Report.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Qwen3 Technical Report

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:15.763798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a3f8a75-d6d7-495f-847e-ebb409b358d8 · outbound

This paper cites The claude 3 model family: Opus, sonnet, haiku.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models The claude 3 model family: Opus, sonnet, haiku

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:46:21.302997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a52540cb-3136-40f1-9737-d157728bb96e · outbound

This paper cites Gemini 2.5: Our most intelligent ai model.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Gemini 2.5: Our most intelligent ai model

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:46:21.136324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d58b01ac-6ffd-40bc-99e7-ddeb6c51d6a1 · outbound

This paper cites Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744, 2022.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744, 2022

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:16.088948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 882703b5-905e-4b4c-930c-1981a69dabf2 · outbound

This paper cites Gonzalez, Ion Stoica, and Eric P.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Gonzalez, Ion Stoica, and Eric P

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:16.218380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a8d7e7c-9318-410a-aa65-476247317808 · outbound

This paper cites Tree of thoughts: Deliberate problem solving with large language models.Ad- vances in neural information processing systems, 36:11809–11822, 2023.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Tree of thoughts: Deliberate problem solving with large language models.Ad- vances in neural information processing systems, 36:11809–11822, 2023

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:46:20.998651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ec49cccf-7992-40b4-a64d-5ecc9d347567 · outbound

This paper cites Solving Quantitative Reasoning Problems with Language Models.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Solving Quantitative Reasoning Problems with Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:16.437950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5d9e47d-c398-45cc-954c-412e79e193a6 · outbound

This paper cites Llemma: An Open Language Model For Mathematics.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Llemma: An Open Language Model For Mathematics

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:16.510056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbc6d12e-8114-4a66-9b0d-888f4d731bb3 · outbound

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

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:16.580693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a95c3f4c-3b47-43b8-8326-63362f7f26a0 · outbound

This paper cites Singhal, Shekoofeh Azizi, Tao Tu, Said Mahdavi, Jason Wei, Hyung Won Chung, Nathan Scales, Ajay Kumar Tanwani, Heather J.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Singhal, Shekoofeh Azizi, Tao Tu, Said Mahdavi, Jason Wei, Hyung Won Chung, Nathan Scales, Ajay Kumar Tanwani, Heather J

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:46:20.777524Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 91e36603-5648-411d-9b06-5a3191e0e7d6 · outbound

This paper cites Galactica: A Large Language Model for Science.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Galactica: A Large Language Model for Science

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:16.779929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24585f50-901c-4667-a70e-ff14201be228 · outbound

This paper cites PAL: Program-aided Language Models.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models PAL: Program-aided Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:16.840640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e4a432b-3084-432d-86e8-53c2b39fbcdc · outbound

This paper cites Contrastive decoding: Open-ended text generation as optimization.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Contrastive decoding: Open-ended text generation as optimization

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:46:20.470870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e3072380-ce34-40b6-b81c-d04493c30428 · outbound

This paper cites Reasoning with Language Model is Planning with World Model.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Reasoning with Language Model is Planning with World Model

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:17.041421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8694828c-2bb2-4f8b-acde-9d3ae93b6fb4 · outbound

This paper cites rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:17.111371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a604b63f-412b-4c28-8665-61ba43c4067f · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:17.185091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df669bc7-cd76-47eb-a157-6b28c25709b5 · outbound

This paper cites Improve Mathematical Reasoning in Language Models by Automated Process Supervision.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Improve Mathematical Reasoning in Language Models by Automated Process Supervision

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:17.253752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2aaea01-99ee-49a8-a32a-c7a4b00cad30 · outbound

This paper cites An Investigation of Neuron Activation as a Unified Lens to Explain Chain-of-Thought Eliciting Arithmetic Reasoning of LLMs.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models An Investigation of Neuron Activation as a Unified Lens to Explain Chain-of-Thought Eliciting Arithmetic Reasoning of LLMs

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:46:19.783962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5a9080bb-fe0a-4a60-b29a-2bdaf9a9141c · outbound

This paper cites Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:17.456419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 280d9557-3591-4f8e-bb70-b23d8bb717bd · outbound

This paper cites Adaptive group policy optimization: Towards stable training and token-efficient reasoning.arXiv preprint arXiv:2503.15952, 2025.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Adaptive group policy optimization: Towards stable training and token-efficient reasoning.arXiv preprint arXiv:2503.15952, 2025

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:17.507037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7818414-6f38-458f-88c9-6ff2bb6c12b0 · outbound

This paper cites Hybrid Group Relative Policy Optimization: A Multi-Sample Approach to Enhancing Policy Optimization.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Hybrid Group Relative Policy Optimization: A Multi-Sample Approach to Enhancing Policy Optimization

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:17.575076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73c61492-c207-493b-b743-8d840017c1c7 · outbound

This paper cites Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:17.653974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56129202-155c-4b44-b60c-5f814e81e76f · outbound

This paper cites OpenCodeReasoning: Advancing Data Distillation for Competitive Coding.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models OpenCodeReasoning: Advancing Data Distillation for Competitive Coding

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:17.745772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1e2b873-a893-4c88-b3fd-dbeb39faed09 · outbound

This paper cites Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:17.819907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08a11087-c695-4a85-9fc5-b371f3689e75 · outbound

This paper cites Generative Verifiers: Reward Modeling as Next-Token Prediction.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Generative Verifiers: Reward Modeling as Next-Token Prediction

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:17.879108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de830069-0ffe-4f12-9223-cbcb7e7b65ad · outbound

This paper cites Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:17.955106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 687e9e94-984b-4701-8346-dee63e3cf51e · outbound

This paper cites Virgo: A Preliminary Exploration on Reproducing o1-like MLLM.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Virgo: A Preliminary Exploration on Reproducing o1-like MLLM

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:18.053402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b8f1d57-e4d7-438e-b76e-6815bbb8b4cb · outbound

This paper cites Towards Best Practices of Activation Patching in Language Models: Metrics and Methods.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Towards Best Practices of Activation Patching in Language Models: Metrics and Methods

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:18.130716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc743eb7-19c7-462e-849b-906f7c8757b2 · outbound

This paper cites Transformer Feed-Forward Layers Are Key-Value Memories.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Transformer Feed-Forward Layers Are Key-Value Memories

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:18.259222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd8655f5-1f3f-47ba-b36d-2ec22f393a16 · outbound

This paper cites Knowledge Neurons in Pretrained Transformers.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Knowledge Neurons in Pretrained Transformers

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:18.445140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65ded547-b1db-4eed-9e2a-beba40408413 · outbound

This paper cites Discovering Latent Knowledge in Language Models Without Supervision.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Discovering Latent Knowledge in Language Models Without Supervision

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:18.554798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97eb0a9c-ef87-4b91-82f6-c5293fd136d3 · outbound

This paper cites Qwen2.5-VL Technical Report.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Qwen2.5-VL Technical Report

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:18.715283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6f0ae5f-8eb5-4980-9248-8ede6b81bc37 · outbound

This paper cites Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments, 2024.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments, 2024

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:18.900360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcc5a936-bb88-4679-b1aa-b062bec97917 · outbound

This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T14:46:19.068265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 35d16542-ddcf-4da5-ab10-74fa647dbe5e · inbound

Logit Arithmetic Elicits Long Reasoning Capabilities Without Training cites this paper.

Logit Arithmetic Elicits Long Reasoning Capabilities Without Training Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-06T16:46:01.206824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c83d2c6-46e2-487f-8a52-dcfd307ef04f · inbound

How Do Answer Tokens Read Reasoning Traces? Self-Reading Patterns in Thinking LLMs for Quantitative Reasoning cites this paper.

How Do Answer Tokens Read Reasoning Traces? Self-Reading Patterns in Thinking LLMs for Quantitative Reasoning Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T02:43:24.271450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cc8530d0-91bb-4a13-94f0-af3e59b18185 · inbound

Behavior Cue Reasoning: Monitorable Reasoning Improves Efficiency and Safety through Oversight cites this paper.

Behavior Cue Reasoning: Monitorable Reasoning Improves Efficiency and Safety through Oversight Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:00:56.558182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 34b3be45-69f3-4bf4-85d5-579ae8baf3e0 · inbound

Behavior Cue Reasoning: Monitorable Reasoning Improves Efficiency and Safety through Oversight cites this paper.

Behavior Cue Reasoning: Monitorable Reasoning Improves Efficiency and Safety through Oversight Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-21T08:29:52.710579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cd84f755-6010-41a1-bfe5-ef48de2732e7 · inbound

The Tell-Tale Norm: $\ell_2$ Magnitude as a Signal for Reasoning Dynamics in Large Language Models cites this paper.

The Tell-Tale Norm: $\ell_2$ Magnitude as a Signal for Reasoning Dynamics in Large Language Models Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T12:26:56.898852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation daf9a472-aa0c-4a06-87e8-08ac9422204f · inbound

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning cites this paper.

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models

Reference 73

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T20:38:55.955665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.