Paper Citation Record · LEDGER

Revisiting LLM Reasoning via Information Bottleneck

As of 18 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 5 inbound Pith citation observations for arXiv:2507.18391.

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

pith.paper-citation-record.v1
2507.18391 v1

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T18:21:08.555405Z

measured 31 of 31 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T14:45:37.426688Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-18T18:31:44.611173Z

Reference resolution

26 of 26 outbound references displayed

verified exact1
verified fuzzy3
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2a7529d4-b8f5-4a22-b79f-ba64f9d1f1d2 · outbound

This paper cites Training language models to follow instructions with human feedback.

Revisiting LLM Reasoning via Information Bottleneck Training language models to follow instructions with human feedback

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:08.320500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1611a904-9368-4fa7-8ee1-9674d51be878 · outbound

This paper cites OpenAI o1 System Card.

Revisiting LLM Reasoning via Information Bottleneck OpenAI o1 System Card

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:08.327634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 193a10d9-63cd-400c-804b-181e67687cc6 · outbound

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

Revisiting LLM Reasoning via Information Bottleneck DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:08.335428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cec214d-853b-41c7-91a3-5b196632a34d · outbound

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

Revisiting LLM Reasoning via Information Bottleneck The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:08.342231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc130e31-d274-4e06-9d93-05cb6a128d2c · outbound

This paper cites Reasoning with Exploration: An Entropy Perspective.

Revisiting LLM Reasoning via Information Bottleneck Reasoning with Exploration: An Entropy Perspective

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:08.349102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 016890d6-cc52-4f80-82b0-13d438ca4d5a · outbound

This paper cites Diversity-aware policy optimization for large language model reasoning.

Revisiting LLM Reasoning via Information Bottleneck Diversity-aware policy optimization for large language model reasoning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:08.358014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c495eb06-2334-428c-9726-44a73613d688 · outbound

This paper cites The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning.

Revisiting LLM Reasoning via Information Bottleneck The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:08.364352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48ee6a67-a6b9-4c1a-802f-d87700e28cc0 · outbound

This paper cites One-shot Entropy Minimization.

Revisiting LLM Reasoning via Information Bottleneck One-shot Entropy Minimization

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:08.371047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b606fae2-3e58-4654-a66b-1e6442e05a64 · outbound

This paper cites Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models.

Revisiting LLM Reasoning via Information Bottleneck Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:08.381567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef29466a-18b2-4ffd-8c6b-54af4b9f63a0 · outbound

This paper cites The information bottleneck method.

Revisiting LLM Reasoning via Information Bottleneck The information bottleneck method

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:08.394685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52ec288a-67c7-434f-91a2-2adcb23feb4e · outbound

This paper cites Deep learning and the information bottleneck principle.

Revisiting LLM Reasoning via Information Bottleneck Deep learning and the information bottleneck principle

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:08.406828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8a6cbce-758d-40af-ac2a-5dcad0fbbe61 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Revisiting LLM Reasoning via Information Bottleneck Proximal Policy Optimization Algorithms

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:08.417886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b276f41-8b64-4c5f-a3b0-89984e75a915 · outbound

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

Revisiting LLM Reasoning via Information Bottleneck DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:08.440400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5baeb517-c260-4fb6-8bec-8c4401bb6c21 · outbound

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

Revisiting LLM Reasoning via Information Bottleneck DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:08.450942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a45967e8-f1c7-4192-b346-7941246b4e6d · outbound

This paper cites Qwen2.5 Technical Report.

Revisiting LLM Reasoning via Information Bottleneck Qwen2.5 Technical Report

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:08.458013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76b44746-b628-4b69-88d0-f6d7f6eeed61 · outbound

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

Revisiting LLM Reasoning via Information Bottleneck Chain-of-thought prompting elicits reasoning in large language models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:08.466984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49e2e3fa-71f4-48ae-a96f-bb2b524efc66 · outbound

This paper cites Alemi, Ian Fischer, Joshua V.

Revisiting LLM Reasoning via Information Bottleneck Alemi, Ian Fischer, Joshua V

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:21:09.440840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4ba06770-7dd5-46b2-8712-ba72fa0e79db · outbound

This paper cites On the information bottleneck theory of deep learning.

Revisiting LLM Reasoning via Information Bottleneck On the information bottleneck theory of deep learning

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:21:09.415682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2ec6101f-588b-4bce-85e7-f5ead91e5556 · outbound

This paper cites How does information bottleneck help deep learning? In International Conference on Machine Learning, pages 16049–16096.

Revisiting LLM Reasoning via Information Bottleneck How does information bottleneck help deep learning? In International Conference on Machine Learning, pages 16049–16096

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:08.493845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abf63ac7-31b0-40d3-8dcb-83d2b21bed6e · outbound

This paper cites Memorization-compression cycles improve generalization.arXiv preprint arXiv:2505.08727, 2025.

Revisiting LLM Reasoning via Information Bottleneck Memorization-compression cycles improve generalization.arXiv preprint arXiv:2505.08727, 2025

Reference 20

Resolution: verified exact; raw_fallback, observed 2026-08-15T18:21:08.962435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5a719c3a-e967-4fdf-bd8f-d2007e949da0 · outbound

This paper cites Measures of entropy from data using infinitely divisible kernels.

Revisiting LLM Reasoning via Information Bottleneck Measures of entropy from data using infinitely divisible kernels

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:21:09.373976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3f857dcd-b5b4-4001-8e1e-5daf622450d4 · outbound

This paper cites Reinforcement learning finetunes small subnetworks in large language models.

Revisiting LLM Reasoning via Information Bottleneck Reinforcement learning finetunes small subnetworks in large language models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:08.527633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c66237ac-2488-4d6f-ab4d-b9cedacdffed · outbound

This paper cites Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them.

Revisiting LLM Reasoning via Information Bottleneck Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:08.532925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b697f1f-c099-41df-ad6c-c211b91966d0 · outbound

This paper cites Hybridflow: A flexible and efficient rlhf framework.

Revisiting LLM Reasoning via Information Bottleneck Hybridflow: A flexible and efficient rlhf framework

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:08.541671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97b2afa1-a7c5-4363-961a-7e3d293c05a7 · outbound

This paper cites Skywork Open Reasoner 1 Technical Report.

Revisiting LLM Reasoning via Information Bottleneck Skywork Open Reasoner 1 Technical Report

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:08.547652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa18ef4b-7416-40ea-a7b3-0d7e23549957 · outbound

This paper cites Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training.

Revisiting LLM Reasoning via Information Bottleneck Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:08.555405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 056a1231-6383-4588-9127-0b041157bfd4 · inbound

Self-Aligned Reward: Towards Effective and Efficient Reasoners cites this paper.

Self-Aligned Reward: Towards Effective and Efficient Reasoners Revisiting LLM Reasoning via Information Bottleneck

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-18T18:31:44.613691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6381c5ad-47e7-4203-855e-b7901e1a5ba8 · inbound

When Less is Enough: Efficient Inference via Collaborative Reasoning cites this paper.

When Less is Enough: Efficient Inference via Collaborative Reasoning Revisiting LLM Reasoning via Information Bottleneck

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-11T15:41:42.284856Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 17f774f1-b33b-4207-8472-db459de00a8b · inbound

Think Through a Bottleneck: Hourglass Reasoning for Rigorous Induction cites this paper.

Think Through a Bottleneck: Hourglass Reasoning for Rigorous Induction Revisiting LLM Reasoning via Information Bottleneck

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-14T03:48:31.314623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9874472e-b237-404e-a4d5-143919ad7257 · inbound

Information-Theoretic Limits of Reliability and Scaling in Language Models cites this paper.

Information-Theoretic Limits of Reliability and Scaling in Language Models Revisiting LLM Reasoning via Information Bottleneck

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T14:45:37.426688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d47ed9d-be70-458f-ac3e-f1b4e783acb8 · inbound

Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization cites this paper.

Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization Revisiting LLM Reasoning via Information Bottleneck

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T01:39:05.465608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.