EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation | Paper Citation Record

Observation 7553e068-703d-4ea9-b922-0ba1f3cb8889 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.Advances in neural information processing systems, 35:24824–24837, 2022.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Chain-of-thought prompting elicits reasoning in large language models.Advances in neural information processing systems, 35:24824–24837, 2022

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.561414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50f87e97-a253-44ae-ac0b-44a8b78d8e6a · outbound

This paper cites Let’s verify step by step.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Let’s verify step by step

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.565459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fd0f809-d993-4ac4-8ea0-e48496cc9145 · outbound

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

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Gpqa: A graduate-level google-proof q&a benchmark

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.576451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddc22cce-f9d7-46fc-b52d-4d52b1e54917 · outbound

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

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.579885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbecbb67-53bf-4cad-836a-d7baaeee0af9 · outbound

This paper cites Open r1: A fully open reproduction of deepseek-r1, January 2025.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Open r1: A fully open reproduction of deepseek-r1, January 2025

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.583827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 195b63ab-3ea6-489d-aa90-7f25ddbe0d50 · outbound

This paper cites Open Thoughts.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Open Thoughts

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.586794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af91db63-914f-4f15-846c-b4f0d20c1ef8 · outbound

This paper cites s1: Simple test-time scaling.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation s1: Simple test-time scaling

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.589581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7777abc1-fd26-42ad-8b8f-9d2b9a8b2d3b · outbound

This paper cites LIMO: Less is More for Reasoning.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation LIMO: Less is More for Reasoning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.592653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee49e7df-3b1f-41f7-8c25-5f8595217cf2 · outbound

This paper cites Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.595462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02cac6bf-36c2-461b-b13f-783b4d571ac2 · outbound

This paper cites Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.599042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e091742-8cc5-4d2d-b6a8-15fa6949332e · outbound

This paper cites Teaching Algorithmic Reasoning via In-context Learning.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Teaching Algorithmic Reasoning via In-context Learning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.602032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d4ee36d-7bc7-4e4f-8264-c855b315397a · outbound

This paper cites Distilling reasoning capabilities into smaller language models.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Distilling reasoning capabilities into smaller language models

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:52:50.625911Z

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 e5701677-c9d1-41f6-ab14-165bb5d1c76f · outbound

This paper cites Specializing smaller language models towards multi-step reasoning.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Specializing smaller language models towards multi-step reasoning

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:52:50.616204Z

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 1c158de0-7333-4b42-a14a-49b51b670ad6 · outbound

This paper cites Generalthought-195k.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Generalthought-195k

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:52:50.607001Z

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 2f37a542-5d93-4922-afa8-2dbfaf206b10 · outbound

This paper cites Sky-t1: Train your own o1 preview model within $450.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Sky-t1: Train your own o1 preview model within $450

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:52:50.597853Z

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 93843c2a-49ba-48e3-9d0c-781d19a30cab · outbound

This paper cites Bespoke-stratos: The unreasonable effectiveness of reasoning distillation.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Bespoke-stratos: The unreasonable effectiveness of reasoning distillation

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.622263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e8cc1a5-c084-4221-ac3d-a6e3ebf81d9f · outbound

This paper cites Re-distilling smaller deepseek r1 models for better performance, January 2025.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Re-distilling smaller deepseek r1 models for better performance, January 2025

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:52:50.575878Z

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 b67a320c-a385-418c-9cb2-ac8cc0a2f360 · outbound

This paper cites Small models struggle to learn from strong reasoners.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Small models struggle to learn from strong reasoners

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.627835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 292b9609-9766-4900-a4d7-9b02281e81cf · outbound

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

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.630323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa8cbb43-9442-421d-a8db-d66217ecef7d · outbound

This paper cites The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.633523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2862761c-9bea-4600-9376-da6e85da8cd7 · outbound

This paper cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.636416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab17a2dc-1f40-4848-b9d5-d2a57f276ad7 · outbound

This paper cites Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.639054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec81d348-18a7-4294-80fd-43521d69084a · outbound

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

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.642382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac419b76-f34b-485f-9ab3-204195e48e25 · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.645112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e8fc576-de5a-4077-a0db-c7d85e05a2dd · outbound

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

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.647879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24fde902-077c-4fba-bc4f-1895e8a99332 · outbound

This paper cites Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.650755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22c3ab18-3fc2-4c39-9110-3702a75f7411 · outbound

This paper cites Large Language Monkeys: Scaling Inference Compute with Repeated Sampling.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Large Language Monkeys: Scaling Inference Compute with Repeated Sampling

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.653723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33260b3a-5eda-464a-be41-d96f88e50944 · outbound

This paper cites Tree of Thoughts: Deliberate Problem Solving with Large Language Models.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Tree of Thoughts: Deliberate Problem Solving with Large Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.657309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fffaa7c-c3cf-4c90-a600-e3b2b07038c1 · outbound

This paper cites DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.660122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d3d6509-1b72-4bc0-9dbe-98e0cdd70a1c · outbound

This paper cites Generat- ing sequences by learning to self-correct.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Generat- ing sequences by learning to self-correct

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:52:50.566674Z

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 954b2356-6baf-43bb-8a3a-55e8fb620164 · outbound

This paper cites Self-Refine: Iterative Refinement with Self-Feedback.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Self-Refine: Iterative Refinement with Self-Feedback

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.669276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ae6e127-f190-44a8-a724-e4e65beda43c · outbound

This paper cites From decoding to meta-generation: Inference-time algorithms for large language models,.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation From decoding to meta-generation: Inference-time algorithms for large language models,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:52:50.547842Z

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 df98069d-c01a-4be8-a355-bf5788b300b8 · outbound

This paper cites Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.678833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dad952b-f63e-466c-ad18-00dbd4330eb0 · outbound

This paper cites L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.682029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85b05d1e-a5fb-488f-b15f-ce1a24ef4d6b · outbound

This paper cites O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.685088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e415a5cc-c3c6-439f-93cb-5fbc81e808a2 · outbound

This paper cites Tokenskip: Controllable chain-of-thought compression in llms.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Tokenskip: Controllable chain-of-thought compression in llms

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.687820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd3a15e7-32cf-4d3b-aed4-a13496f0d60b · outbound

This paper cites Lightthinker: Thinking step-by-step compression.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Lightthinker: Thinking step-by-step compression

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.690806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7717239d-8a7a-4d08-97f6-dd607b20b9f7 · outbound

This paper cites Similar: Submodular information measures based active learning in realistic scenarios.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Similar: Submodular information measures based active learning in realistic scenarios

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:52:50.538230Z

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 b0d60cd4-46fd-45a8-a180-5172c1066f19 · outbound

This paper cites GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.697076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f0b9125-7aaa-41fe-9713-d48a9a0e84c2 · outbound

This paper cites Deduplicating Training Data Makes Language Models Better.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Deduplicating Training Data Makes Language Models Better

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.699909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d7a7f66-6f0f-4f61-b53f-1ce86d42f75c · outbound

This paper cites Dataset pruning for resource-constrained spoofed audio detection.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Dataset pruning for resource-constrained spoofed audio detection

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:52:50.528742Z

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 1e0e364c-f685-41d0-9fa9-439fd248fe3e · outbound

This paper cites Contextual diversity for active learning.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Contextual diversity for active learning

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:52:50.520002Z

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 1f85362d-36e4-43f4-aac3-915b1cff94a6 · outbound

This paper cites Selection via Proxy: Efficient Data Selection for Deep Learning.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Selection via Proxy: Efficient Data Selection for Deep Learning

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.708522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87e23ff1-7ecd-480f-b882-04e06473a068 · outbound

This paper cites Active learning is a strong baseline for data subset selection.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Active learning is a strong baseline for data subset selection

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:52:50.511019Z

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 627d5ee4-0d74-47b6-a819-e74f223fa45b · outbound

This paper cites Coresets for data-efficient training of machine learning models.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Coresets for data-efficient training of machine learning models

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:52:50.501816Z

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 8866c768-dc99-4b75-8919-3d6ccde2859e · outbound

This paper cites An Empirical Study of Example Forgetting during Deep Neural Network Learning.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation An Empirical Study of Example Forgetting during Deep Neural Network Learning

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.717004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f877161-bec9-431a-9ce1-017f6992099d · outbound

This paper cites Deep learning on a data diet: Finding important examples early in training.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Deep learning on a data diet: Finding important examples early in training

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.719767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c295cae3-eb0a-489c-8b56-786356d1ea2b · outbound

This paper cites Fewer is More: Boosting LLM Reasoning with Reinforced Context Pruning.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Fewer is More: Boosting LLM Reasoning with Reinforced Context Pruning

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.722603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bace416-87e2-43e9-9152-520cdf5dcb52 · outbound

This paper cites Staff: Specu- lative coreset selection for task-specific fine-tuning.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Staff: Specu- lative coreset selection for task-specific fine-tuning

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:52:50.486551Z

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 c2e64d93-be90-45dc-b914-c03dbf45b9ce · outbound

This paper cites LESS: Selecting Influential Data for Targeted Instruction Tuning.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation LESS: Selecting Influential Data for Targeted Instruction Tuning

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.728829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dce7c1fa-8955-4eca-b5ed-8c3abc88b223 · outbound

This paper cites Lima: Less is more for alignment.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Lima: Less is more for alignment

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:52:50.476706Z

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 5611cfc9-3ddf-4b9b-823c-ac5fb56c7e39 · outbound

This paper cites OpenAI o1 System Card.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation OpenAI o1 System Card

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.734344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bde1899b-7687-464e-a0de-9d3016f4d899 · outbound

This paper cites Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.737129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6d45ce7-ba34-4679-bd80-49b8aa172fb1 · outbound

This paper cites LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.739784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59ca9d86-e389-49b8-8d27-c2c2cf0496b6 · outbound

This paper cites Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.742589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e4f9db4-eb03-49f9-93fe-6679630c599b · outbound

This paper cites Land- scape of thoughts: Visualizing the reasoning process of large language models.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Land- scape of thoughts: Visualizing the reasoning process of large language models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.745278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8525c51-7dc8-4bcd-bfaa-57e1b822fb37 · outbound

This paper cites Estimating mutual information.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Estimating mutual information

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.748222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fa628d8-a111-49da-bcc2-bb35d46ca8b5 · outbound

This paper cites Pointer sentinel mixture models, 2016.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Pointer sentinel mixture models, 2016

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.750747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f255497d-6f64-47a9-83c7-2e0d11c5270c · outbound

This paper cites Math-verify: Math verification library, 2024.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Math-verify: Math verification library, 2024

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:52:50.454743Z

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 e2818539-ad52-4a83-8805-e7d8b4f331cb · outbound

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

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.756502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a818a938-fc08-46d3-a528-d6681a357f7c · outbound

This paper cites Qwen2.5 Technical Report.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Qwen2.5 Technical Report

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.759907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb333f73-2947-4d11-b394-2c2cac17f800 · outbound

This paper cites The Llama 3 Herd of Models.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation The Llama 3 Herd of Models

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b486ab1-7932-4020-bbfd-c639a059e38a · outbound

This paper cites Aime problems and solutions.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Aime problems and solutions

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:52:50.444190Z

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 fe61110a-0fb6-48b3-b523-7bf880605ae6 · outbound

This paper cites an unresolved cited work.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Unresolved cited work

Reference 2023

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:52:50.557367Z

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 4a6f70b4-328a-4871-bfd8-7e74942e7ec9 · outbound

This paper cites From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.675555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 877e747a-fb37-44e0-b48f-da98313338e3 · outbound

This paper cites an unresolved cited work.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation Unresolved cited work

Reference 2025

Resolution: parse uncertain; no resolver link, observed 2026-08-07T10:52:49.619568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers