Paper Citation Record · LEDGER

Saffron-1: Safety Inference Scaling

As of 8 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 1 inbound Pith citation observation for arXiv:2506.06444.

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

pith.paper-citation-record.v1
2506.06444 v2

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T06:02:25.916469Z

measured 31 of 31 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T10:39:06.998121Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

30 of 30 outbound references displayed

verified exact2
verified fuzzy5
unresolved23
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5d02b4c5-1624-42d6-aff7-f504e9300542 · outbound

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

Saffron-1: Safety Inference Scaling Large Language Monkeys: Scaling Inference Compute with Repeated Sampling

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T06:02:25.813428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24b8f4dd-b16e-42ec-9539-ea095a1b0517 · outbound

This paper cites Chan, Jui-Hung Cheng, Mao Xun Huang, Chao-Ting Chen, and Hen-Hsen Huang.

Saffron-1: Safety Inference Scaling Chan, Jui-Hung Cheng, Mao Xun Huang, Chao-Ting Chen, and Hen-Hsen Huang

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T06:02:25.817677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd5cc94e-9825-4a77-835d-6d9122f0e074 · outbound

This paper cites Group fairness via group consensus.

Saffron-1: Safety Inference Scaling Group fairness via group consensus

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T06:02:26.755608Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b1d870e0-da28-42a6-829b-a9028a492b00 · outbound

This paper cites WAPITI: A Watermark for Finetuned Open-Source LLMs.

Saffron-1: Safety Inference Scaling WAPITI: A Watermark for Finetuned Open-Source LLMs

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-08-07T06:02:26.541186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ca556af4-5b6f-43f9-905c-a985acb323db · outbound

This paper cites Rm-r1: Reward modeling as reasoning.arXiv preprint arXiv:2505.02387,.

Saffron-1: Safety Inference Scaling Rm-r1: Reward modeling as reasoning.arXiv preprint arXiv:2505.02387,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T06:02:25.830083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c109cc7b-338a-48e4-8cda-b61376d2f70f · outbound

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

Saffron-1: Safety Inference Scaling DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T06:02:25.833832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb77d116-b274-4552-b351-e310acc6a5e7 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

Saffron-1: Safety Inference Scaling Distilling the Knowledge in a Neural Network

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T06:02:25.837826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50dbe9f6-cc3c-4606-a1ce-937fccbd5681 · outbound

This paper cites Huang, Sailik Sengupta, Daniele Bonadiman, Yi-an Lai, Arshit Gupta, Nikolaos Pappas, Saab Mansour, Katrin Kirchhoff, and Dan Roth.

Saffron-1: Safety Inference Scaling Huang, Sailik Sengupta, Daniele Bonadiman, Yi-an Lai, Arshit Gupta, Nikolaos Pappas, Saab Mansour, Katrin Kirchhoff, and Dan Roth

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T06:02:25.845838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59ae1677-fd09-432f-a926-d582bf0fa8d3 · outbound

This paper cites Model-free graph data selection under distribution shift.arXiv preprint arXiv:2505.17293, 2025a.

Saffron-1: Safety Inference Scaling Model-free graph data selection under distribution shift.arXiv preprint arXiv:2505.17293, 2025a

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T06:02:25.853332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31f44421-3ffd-404a-a582-d439fb0c3376 · outbound

This paper cites Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs.

Saffron-1: Safety Inference Scaling Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T06:02:25.856630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cf43577-ad33-4b59-8585-f8bc50c62ee6 · outbound

This paper cites Class-imbalanced graph learning without class rebalancing.

Saffron-1: Safety Inference Scaling Class-imbalanced graph learning without class rebalancing

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T06:02:26.742265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ad1c8170-f1f3-4b98-b887-a95067ce60f6 · outbound

This paper cites Rule Based Rewards for Language Model Safety.

Saffron-1: Safety Inference Scaling Rule Based Rewards for Language Model Safety

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T06:02:25.867442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 001fc83e-79c6-404a-80d5-5202aedabe33 · outbound

This paper cites GPT-4 Technical Report.

Saffron-1: Safety Inference Scaling GPT-4 Technical Report

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T06:02:25.872021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29506041-8e66-498b-9629-265f86f062d8 · outbound

This paper cites OpenAI o1 System Card.

Saffron-1: Safety Inference Scaling OpenAI o1 System Card

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T06:02:25.875537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d056f852-f55b-46ae-ad7d-fc106b8bcbd1 · outbound

This paper cites Reconstructing graph diffusion history from a single snapshot.

Saffron-1: Safety Inference Scaling Reconstructing graph diffusion history from a single snapshot

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T06:02:26.729428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 756daa71-4fdb-40ec-a3be-f8490c98192b · outbound

This paper cites do anything now.

Saffron-1: Safety Inference Scaling do anything now

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T06:02:26.716829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b81a66a0-0446-435f-92da-f2479f9723c9 · outbound

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

Saffron-1: Safety Inference Scaling Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T06:02:25.886327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72be71cf-0c7e-4576-a367-8697020cb15d · outbound

This paper cites Bypassing the Safety Training of Open-Source LLMs with Priming Attacks.

Saffron-1: Safety Inference Scaling Bypassing the Safety Training of Open-Source LLMs with Priming Attacks

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T06:02:25.890123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3032f056-8384-4bfe-8e22-04848bb30f25 · outbound

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

Saffron-1: Safety Inference Scaling Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T06:02:25.893745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d1e9ce5-fb57-4d22-a606-eeac6cec649a · outbound

This paper cites Fair Anomaly Detection For Imbalanced Groups.

Saffron-1: Safety Inference Scaling Fair Anomaly Detection For Imbalanced Groups

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-08-07T06:02:26.142501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2077d018-7f44-4198-876e-d60717390b84 · outbound

This paper cites Ensuring user-side fairness in dynamic recommender systems.

Saffron-1: Safety Inference Scaling Ensuring user-side fairness in dynamic recommender systems

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T06:02:26.704565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 57fd0848-0280-4069-9452-33e34040186a · outbound

This paper cites Abdelza- her, Jiawei Han, and Hanghang Tong.

Saffron-1: Safety Inference Scaling Abdelza- her, Jiawei Han, and Hanghang Tong

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T06:02:25.905900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29171856-4ebc-4e54-82ae-c81cd49d84c9 · outbound

This paper cites The Lessons of Developing Process Reward Models in Mathematical Reasoning.

Saffron-1: Safety Inference Scaling The Lessons of Developing Process Reward Models in Mathematical Reasoning

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T06:02:25.912510Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 582b2241-230b-4985-be30-928542f3a0cb · outbound

This paper cites Transformer copilot: Learning from the mistake log in LLM fine-tuning.arXiv preprint arXiv:2505.16270,.

Saffron-1: Safety Inference Scaling Transformer copilot: Learning from the mistake log in LLM fine-tuning.arXiv preprint arXiv:2505.16270,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T06:02:25.916469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62869168-c707-46cb-b891-5d413d74a27c · outbound

This paper cites The Curious Case of Neural Text Degeneration.

Saffron-1: Safety Inference Scaling The Curious Case of Neural Text Degeneration

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-07T06:02:25.841775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9e09cf3-21fe-4d34-a920-f96f687101a1 · outbound

This paper cites The Llama 3 Herd of Models.

Saffron-1: Safety Inference Scaling The Llama 3 Herd of Models

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-07T06:02:25.863931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 972c1835-d789-4249-9d43-16e6bb3a105c · outbound

This paper cites InfAlign: Inference-aware language model alignment.

Saffron-1: Safety Inference Scaling InfAlign: Inference-aware language model alignment

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T06:02:25.803951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 572c1b5b-3620-4b18-9e08-805d655e69bd · outbound

This paper cites RewardBench: Evaluating Reward Models for Language Modeling.

Saffron-1: Safety Inference Scaling RewardBench: Evaluating Reward Models for Language Modeling

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T06:02:25.849371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d2422cc-5f7a-453c-9cf4-7df4670ccb21 · outbound

This paper cites Theoretical guarantees on the best-of-n alignment policy.

Saffron-1: Safety Inference Scaling Theoretical guarantees on the best-of-n alignment policy

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T06:02:25.808950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aacac039-34e5-475c-a7a9-bfe02ccb3abd · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Saffron-1: Safety Inference Scaling Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T06:02:25.798807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation caad090c-df54-44b2-a7c2-2331bec8d32b · inbound

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models cites this paper.

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models Saffron-1: Safety Inference Scaling

Reference 141

Resolution: unresolved; no resolver link, observed 2026-08-05T10:39:06.998121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.