Paper Citation Record · LEDGER

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty

As of 12 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 11 inbound Pith citation observations for arXiv:2506.10446.

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

pith.paper-citation-record.v1
2506.10446 v1

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T04:38:09.532937Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 11 of 11 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T17:54:17.219235Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-10T11:37:03.402806Z

Reference resolution

35 of 35 outbound references displayed

verified exact0
verified fuzzy0
unresolved35
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0069c815-bd16-4231-8173-7a5934c47051 · outbound

This paper cites URL: " 'urlintro :=.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty URL: " 'urlintro :=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.342069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4980ab87-9059-4904-b725-1fbe1c83ae99 · outbound

This paper cites write newline.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.379807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6aeaa226-188c-4a21-a082-b5543e7e2a48 · outbound

This paper cites GPT-4 Technical Report.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty GPT-4 Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.444251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3402a25a-1763-4e0c-a88b-a64da857ae46 · outbound

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

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.447873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 908d5555-fa5d-4423-b0e8-8c01887fd963 · outbound

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

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.450960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b665ca90-4556-469d-b170-c5d81f76ea51 · outbound

This paper cites an unresolved cited work.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.453792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c99523a-ece3-43b6-88ec-2b64a9fcaa15 · outbound

This paper cites Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.456278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7398259e-816c-4ee9-9ffa-ec0a5567b183 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Training Verifiers to Solve Math Word Problems

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.459181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d3c70e8-74e4-4cf2-80e1-95f6f15f6072 · outbound

This paper cites Break the Chain: Large Language Models Can be Shortcut Reasoners.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Break the Chain: Large Language Models Can be Shortcut Reasoners

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.462021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e67df85b-d344-4f51-8833-ae66fee42643 · outbound

This paper cites Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.465060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d298be2c-dca1-4534-b93a-5f0ed09b9553 · outbound

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

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.467858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c883f271-b8c6-46de-be2f-abf7ad3f223f · outbound

This paper cites Token-Budget-Aware LLM Reasoning.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Token-Budget-Aware LLM Reasoning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.470606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7de45b5-aa0c-48ee-85a2-47fc2c432ccc · outbound

This paper cites Qwen2.5-Coder Technical Report.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Qwen2.5-Coder Technical Report

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.473281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95c9409d-08a4-436d-ab34-5940fff60271 · outbound

This paper cites an unresolved cited work.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.476241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1effa212-a6a7-4461-8958-7e997de45ed1 · outbound

This paper cites How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.478670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1c23248-35b3-439c-91e7-dedaa67ed2da · outbound

This paper cites an unresolved cited work.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.481397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29ea50cc-b6d1-4a6c-8b6a-4dc85ddca9ab · outbound

This paper cites Can Language Models Learn to Skip Steps?.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Can Language Models Learn to Skip Steps?

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.483737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37e8aeb8-dd22-4af2-b8fc-8bd33ca73664 · outbound

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

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.487029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e617a0c-4d1c-40c4-9b1c-089b198ab836 · outbound

This paper cites CoT-Valve: Length-Compressible Chain-of-Thought Tuning.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty CoT-Valve: Length-Compressible Chain-of-Thought Tuning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.490360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29ebbd21-de7d-44f0-b298-a49443504355 · outbound

This paper cites Self-Training Elicits Concise Reasoning in Large Language Models.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Self-Training Elicits Concise Reasoning in Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.493118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc246e1e-f44a-4d10-9d85-744785eb390a · outbound

This paper cites an unresolved cited work.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-07T04:38:09.923839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ef1838da-9d3b-4dcc-b568-afde3d122de3 · outbound

This paper cites an unresolved cited work.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.498219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90e46486-f059-4c37-a975-434082a63560 · outbound

This paper cites Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.500490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fd99e05-0f91-4449-858d-59837883ed03 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Proximal Policy Optimization Algorithms

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.503183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b5b2642-3fe4-4aff-9dc8-97c1a30d7232 · outbound

This paper cites Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.506458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4479b550-e857-41f0-be56-da4d091dd45f · outbound

This paper cites Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.509078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35933934-069a-4963-bb2a-00c124f287a4 · outbound

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

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.511814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00c920ab-74c4-4ebe-a797-247384b583c4 · outbound

This paper cites an unresolved cited work.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-07T04:38:09.915907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0b57aabd-de9b-4a89-b2e8-dc5e9ad2cece · outbound

This paper cites an unresolved cited work.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.516893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d873ba20-899e-44a3-a97c-bd6f33e6daff · outbound

This paper cites an unresolved cited work.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.519303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cebeac8f-9693-428e-a446-8303a767d6db · outbound

This paper cites an unresolved cited work.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.521675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b38dbbbf-32d0-4f04-b678-3fbd2a42fdc2 · outbound

This paper cites Chain of Draft: Thinking Faster by Writing Less.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Chain of Draft: Thinking Faster by Writing Less

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.524298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51c8a539-fe39-48dc-9a2c-88b63d6ab88d · outbound

This paper cites an unresolved cited work.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.526904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d12d43a8-1b04-49a0-86fe-b96238f7adae · outbound

This paper cites LIMO: Less is More for Reasoning.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty LIMO: Less is More for Reasoning

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.529187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c333e166-6cdc-4f61-8eb9-33e7b9cf86b2 · outbound

This paper cites Least-to-Most Prompting Enables Complex Reasoning in Large Language Models.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty Least-to-Most Prompting Enables Complex Reasoning in Large Language Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.532937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 1b70cf35-6073-4738-a278-6306d0f96f9e · inbound

Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey cites this paper.

Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty

Reference 105

Resolution: unresolved; no resolver link, observed 2026-08-06T17:54:17.219235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53d96970-d5c3-4493-a872-35f66a92d696 · inbound

Baichuan-M2: Scaling Medical Capability with Large Verifier System cites this paper.

Baichuan-M2: Scaling Medical Capability with Large Verifier System Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-05T11:50:15.945247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 466f95ac-15c9-42fd-8d4e-9166aa94374e · inbound

Baichuan-M2: Scaling Medical Capability with Large Verifier System cites this paper.

Baichuan-M2: Scaling Medical Capability with Large Verifier System Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-05T11:50:16.038483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8665faff-1f48-4338-90cc-d2a77ebdebf2 · inbound

Learning to Reason Efficiently with Discounted Reinforcement Learning cites this paper.

Learning to Reason Efficiently with Discounted Reinforcement Learning Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-04T07:59:52.963465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a3c8790-f987-4c3a-9320-c06007867427 · inbound

Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation cites this paper.

Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-03T03:04:43.959361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51a4b97b-b9c2-44c7-921f-bab23716752b · inbound

Compress the Easy, Explore the Hard: Difficulty-Aware Entropy Regularization for Efficient LLM Reasoning cites this paper.

Compress the Easy, Explore the Hard: Difficulty-Aware Entropy Regularization for Efficient LLM Reasoning Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T20:44:45.635731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 357fa96c-7cad-4d73-ab57-e01601f11fd8 · inbound

PR-CAD: Progressive Refinement for Unified Controllable and Faithful Text-to-CAD Generation with Large Language Models cites this paper.

PR-CAD: Progressive Refinement for Unified Controllable and Faithful Text-to-CAD Generation with Large Language Models Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-14T23:18:15.685504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e22b7477-10a0-4a34-b13e-281a7de1e7e1 · inbound

Reinforcement Learning for Tool-Calling Agents in Fast Healthcare Interoperability Resources (FHIR) cites this paper.

Reinforcement Learning for Tool-Calling Agents in Fast Healthcare Interoperability Resources (FHIR) Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-15T04:59:45.773704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 9b9a0fb6-a743-4d4a-bbc2-5ae534685e3d · inbound

SLAT: Segment-Level Adaptive Trimming for Efficient CoT Reasoning cites this paper.

SLAT: Segment-Level Adaptive Trimming for Efficient CoT Reasoning Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-06-28T22:32:44.446460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a82d171d-7af1-424e-9a02-6588c10dc8c2 · inbound

Beyond Penalizing Mistakes: Stabilizing Efficiency Training in Large Reasoning Models via Adaptive Correct-Only Rewards cites this paper.

Beyond Penalizing Mistakes: Stabilizing Efficiency Training in Large Reasoning Models via Adaptive Correct-Only Rewards Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-07-04T09:19:43.868020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 7aa84793-094d-4c27-bc20-0c9d0a2e9eed · inbound

A First-Principles Theory of Slow Thinking and Active Perception cites this paper.

A First-Principles Theory of Slow Thinking and Active Perception Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty

Reference 103

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T11:37:03.404461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.