Paper Citation Record · LEDGER

Length Penalties Make Chain-of-Thought Less Monitorable

As of 7 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 1 inbound Pith citation observation for arXiv:2607.09786.

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

pith.paper-citation-record.v1
2607.09786 v3

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T04:30:30.646103Z

measured 43 of 43 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T15:22:55.656489Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

42 of 42 outbound references displayed

verified exact0
verified fuzzy0
unresolved42
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 97701c45-53b2-43a6-a8f8-5ae87c201e40 · outbound

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

Length Penalties Make Chain-of-Thought Less Monitorable L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:26.557823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28d8df4c-1a6e-480d-ac42-8561ae3cef0a · outbound

This paper cites MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms.

Length Penalties Make Chain-of-Thought Less Monitorable MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:26.666683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82ffa36e-827e-434b-853f-66e4ade443c8 · outbound

This paper cites Chain-of-Thought Reasoning In The Wild Is Not Always Faithful.

Length Penalties Make Chain-of-Thought Less Monitorable Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:26.776436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 633d15ed-7598-458d-a62d-015ff92eed21 · outbound

This paper cites CoT red-handed: Stress testing chain-of-thought monitoring.

Length Penalties Make Chain-of-Thought Less Monitorable CoT red-handed: Stress testing chain-of-thought monitoring

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:26.891885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9efa272a-b3f8-49d5-94f7-f07f509e066e · outbound

This paper cites Training language models to reason efficiently.

Length Penalties Make Chain-of-Thought Less Monitorable Training language models to reason efficiently

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:27.005827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd77c0cd-8eb6-41d3-916a-1de33f5ed9d8 · outbound

This paper cites Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation.

Length Penalties Make Chain-of-Thought Less Monitorable Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:27.115646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3efc6f17-67e3-4b1e-a489-4700e721431e · outbound

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

Length Penalties Make Chain-of-Thought Less Monitorable Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:27.191039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a03e0ae6-eeb5-4032-b61f-e9d7eee66b59 · outbound

This paper cites Reasoning Models Don't Always Say What They Think.

Length Penalties Make Chain-of-Thought Less Monitorable Reasoning Models Don't Always Say What They Think

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:27.262689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80149489-ac33-4a51-946b-fc884ff6ec92 · outbound

This paper cites Are DeepSeek R1 And Other Reasoning Models More Faithful?.

Length Penalties Make Chain-of-Thought Less Monitorable Are DeepSeek R1 And Other Reasoning Models More Faithful?

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:27.374607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef30e1dc-c058-4e94-95c1-46f0948119e0 · outbound

This paper cites Stable Reinforcement Learning for Efficient Reasoning.

Length Penalties Make Chain-of-Thought Less Monitorable Stable Reinforcement Learning for Efficient Reasoning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:27.449308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41a9d687-c31d-4438-a8e6-4c06cbe6c0d5 · outbound

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

Length Penalties Make Chain-of-Thought Less Monitorable DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:27.554149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03f629ac-98bd-4d01-845c-e27236735a97 · outbound

This paper cites When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors.

Length Penalties Make Chain-of-Thought Less Monitorable When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:27.658275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e5448be-75aa-41b4-bbf9-162edb9f3169 · outbound

This paper cites Guan, Miles Wang, Micah Carroll, Zehao Dou, Annie Y.

Length Penalties Make Chain-of-Thought Less Monitorable Guan, Miles Wang, Micah Carroll, Zehao Dou, Annie Y

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:27.763139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0f799cd-edf0-4487-9baa-cbd49d555b6b · outbound

This paper cites Verbalizable representations form a global workspace in language models.

Length Penalties Make Chain-of-Thought Less Monitorable Verbalizable representations form a global workspace in language models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:27.863626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 091de329-d6a2-4715-ac48-8e198bdf4189 · outbound

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

Length Penalties Make Chain-of-Thought Less Monitorable ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:27.962588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b59b549f-2dca-42ab-b805-c1971cb80f21 · outbound

This paper cites What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams.

Length Penalties Make Chain-of-Thought Less Monitorable What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:28.064643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38c6ebe6-faf7-4b68-b4ab-2d5137eefa4b · outbound

This paper cites Zimmermann, and Rohin Shah.

Length Penalties Make Chain-of-Thought Less Monitorable Zimmermann, and Rohin Shah

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:28.163403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9397e7b6-b61a-44b6-82e0-85d21f18e456 · outbound

This paper cites Large language models are zero-shot reasoners.

Length Penalties Make Chain-of-Thought Less Monitorable Large language models are zero-shot reasoners

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:28.291550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cd93958-929e-4098-bddf-200e0f8b80c0 · outbound

This paper cites Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety.

Length Penalties Make Chain-of-Thought Less Monitorable Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:28.364330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cd7ce18-472e-4807-936b-929d21c8f29b · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

Length Penalties Make Chain-of-Thought Less Monitorable Gonzalez, Hao Zhang, and Ion Stoica

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:28.450839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec706780-0a3f-4c6b-ba0d-fe3d67fbab7e · outbound

This paper cites Measuring Faithfulness in Chain-of-Thought Reasoning.

Length Penalties Make Chain-of-Thought Less Monitorable Measuring Faithfulness in Chain-of-Thought Reasoning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:28.550839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ed3d504-ebaa-4019-a849-091634db5772 · outbound

This paper cites DeepCompress : A dual reward strategy for dynamically exploring and compressing reasoning chains.

Length Penalties Make Chain-of-Thought Less Monitorable DeepCompress : A dual reward strategy for dynamically exploring and compressing reasoning chains

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:28.679145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 508ab95b-bdf7-40d5-8508-8902496dfd05 · outbound

This paper cites an unresolved cited work.

Length Penalties Make Chain-of-Thought Less Monitorable Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:28.775772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 212f73b6-8632-4c75-9ee7-7723f0b457ce · outbound

This paper cites Understanding R1-Zero-Like Training: A Critical Perspective.

Length Penalties Make Chain-of-Thought Less Monitorable Understanding R1-Zero-Like Training: A Critical Perspective

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:28.871469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 140526a6-46cb-4edf-a942-b65a7b27530a · outbound

This paper cites Faithful chain-of-thought reasoning.

Length Penalties Make Chain-of-Thought Less Monitorable Faithful chain-of-thought reasoning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:29.011539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90fa1903-332b-4305-bfb6-29cebb2814ae · outbound

This paper cites Reasoning under pressure: How do training incentives influence chain-of-thought monitorability? arXiv preprint arXiv:2512.00218, 2025.

Length Penalties Make Chain-of-Thought Less Monitorable Reasoning under pressure: How do training incentives influence chain-of-thought monitorability? arXiv preprint arXiv:2512.00218, 2025

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:29.111462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6f18e25-42ec-49db-8372-e96bb50d6913 · outbound

This paper cites Chain-of-thought obfuscation learned from output supervision can generalise to unseen tasks.

Length Penalties Make Chain-of-Thought Less Monitorable Chain-of-thought obfuscation learned from output supervision can generalise to unseen tasks

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:29.213030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62774abb-7bfc-4014-a3cf-75eed839ff2d · outbound

This paper cites s1: Simple test-time scaling.

Length Penalties Make Chain-of-Thought Less Monitorable s1: Simple test-time scaling

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:29.315426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 611fe834-32c6-4fbe-811d-fefe8563d370 · outbound

This paper cites NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model.

Length Penalties Make Chain-of-Thought Less Monitorable NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:29.444171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 153b26d7-159a-4171-8320-f9bffd4cdde9 · outbound

This paper cites OpenAI o1 System Card.

Length Penalties Make Chain-of-Thought Less Monitorable OpenAI o1 System Card

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:29.549813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 931c8414-328a-4505-96ac-e500acd05c13 · outbound

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

Length Penalties Make Chain-of-Thought Less Monitorable DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:29.616907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bc338ce-45be-4bb1-9831-6981065e318a · outbound

This paper cites HybridFlow : A flexible and efficient RLHF framework.

Length Penalties Make Chain-of-Thought Less Monitorable HybridFlow : A flexible and efficient RLHF framework

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:29.701653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 026fc710-db73-4738-9a63-532022000159 · outbound

This paper cites an unresolved cited work.

Length Penalties Make Chain-of-Thought Less Monitorable Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:29.791096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5384e5c-ef90-4c86-a496-3764e3e57b74 · outbound

This paper cites MonitorBench : A comprehensive benchmark for chain-of-thought monitorability in large language models.

Length Penalties Make Chain-of-Thought Less Monitorable MonitorBench : A comprehensive benchmark for chain-of-thought monitorability in large language models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:29.888965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc03df48-b946-4c2e-ab50-44787f31df68 · outbound

This paper cites MMLU-Pro : A more robust and challenging multi-task language understanding benchmark.

Length Penalties Make Chain-of-Thought Less Monitorable MMLU-Pro : A more robust and challenging multi-task language understanding benchmark

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:29.972402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da070da8-6c13-4707-8003-e11d4dcbaa30 · outbound

This paper cites Le, and Denny Zhou.

Length Penalties Make Chain-of-Thought Less Monitorable Le, and Denny Zhou

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:30.064037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c6f5859-2199-4f0b-a129-13d2f68e69a2 · outbound

This paper cites Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning.

Length Penalties Make Chain-of-Thought Less Monitorable Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:30.198277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdf44ff4-68c5-438c-91eb-24e47b2b6d30 · outbound

This paper cites Qwen3 Technical Report.

Length Penalties Make Chain-of-Thought Less Monitorable Qwen3 Technical Report

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:30.288713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a92e59f8-8c6d-4e93-9bd3-3c8af6441ff2 · outbound

This paper cites ShorterBetter : Guiding reasoning models to find optimal inference length for efficient reasoning.

Length Penalties Make Chain-of-Thought Less Monitorable ShorterBetter : Guiding reasoning models to find optimal inference length for efficient reasoning

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:30.356878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89c28c4e-e42b-4702-8416-81ffd83d3c61 · outbound

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

Length Penalties Make Chain-of-Thought Less Monitorable DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:30.469902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adf9c2bf-5861-4f78-89d7-cd8ccaf75bb8 · outbound

This paper cites ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning.

Length Penalties Make Chain-of-Thought Less Monitorable ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:30.561818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 468f8bbb-9c8c-448c-accf-13bc3d193157 · outbound

This paper cites MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark.

Length Penalties Make Chain-of-Thought Less Monitorable MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-04T04:30:30.646103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 6c431f89-a143-491d-b303-ff92ff1eb2f6 · inbound

How Much Does a Reasoning Summary Reveal? An Observability Ladder for Large Language Models cites this paper.

How Much Does a Reasoning Summary Reveal? An Observability Ladder for Large Language Models Length Penalties Make Chain-of-Thought Less Monitorable

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T15:22:55.656489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.