Paper Citation Record · LEDGER

Data-adaptive Safety Rules for Training Reward Models

As of 18 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 3 inbound Pith citation observations for arXiv:2501.15453.

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

pith.paper-citation-record.v1
2501.15453 v2

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T14:25:13.230661Z

measured 34 of 34 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 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:56:15.621439Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T04:19:34.990786Z

Reference resolution

31 of 31 outbound references displayed

verified exact0
verified fuzzy6
unresolved25
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2580469f-61db-4e46-bfda-2c09e04d1bf5 · outbound

This paper cites GPT-4 Technical Report.

Data-adaptive Safety Rules for Training Reward Models GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.088401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27bce344-63e0-43a5-b1e8-cf48a2dcc71c · outbound

This paper cites Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2.

Data-adaptive Safety Rules for Training Reward Models Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.142485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0094cbfa-69e6-4ce1-b644-a9f29f1420e6 · outbound

This paper cites {severe level} harm question:.

Data-adaptive Safety Rules for Training Reward Models {severe level} harm question:

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:25:13.756734Z

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 f470421d-ab73-4e1c-b06d-bb39dce0e019 · outbound

This paper cites SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF.

Data-adaptive Safety Rules for Training Reward Models SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.113800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cafb5bb8-e090-46e9-96e6-715b3ae5428a · outbound

This paper cites Quantile Regression for Distributional Reward Models in RLHF.

Data-adaptive Safety Rules for Training Reward Models Quantile Regression for Distributional Reward Models in RLHF

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.118759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation baeecbd7-6222-423c-bd54-a7e288f10e8e · outbound

This paper cites The Capacity for Moral Self-Correction in Large Language Models.

Data-adaptive Safety Rules for Training Reward Models The Capacity for Moral Self-Correction in Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.128436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61ddd42a-ac36-44ab-bb67-176891b13f68 · outbound

This paper cites Improving alignment of dialogue agents via targeted human judgements.

Data-adaptive Safety Rules for Training Reward Models Improving alignment of dialogue agents via targeted human judgements

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.132837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fce955e-fa59-4530-816f-4f37da03cc29 · outbound

This paper cites Collective Constitutional AI: Aligning a language model with public input.

Data-adaptive Safety Rules for Training Reward Models Collective Constitutional AI: Aligning a language model with public input

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:25:13.815217Z

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 b12fa28a-d167-4fcf-aeb5-fa8ad8b9afc4 · outbound

This paper cites PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference.

Data-adaptive Safety Rules for Training Reward Models PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.146914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a941f6f1-daac-4ccd-922d-6c52dd840f81 · outbound

This paper cites Mistral 7B.

Data-adaptive Safety Rules for Training Reward Models Mistral 7B

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.151591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 778afdcc-4115-4c0f-a689-d5149d6a5281 · outbound

This paper cites Mixtral of Experts.

Data-adaptive Safety Rules for Training Reward Models Mixtral of Experts

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.155955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95b18964-317a-47b4-aff0-a183c9e5f0b2 · outbound

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

Data-adaptive Safety Rules for Training Reward Models RewardBench: Evaluating Reward Models for Language Modeling

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.165585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52271593-4ae9-48d8-9291-b2b50125b6ad · outbound

This paper cites Rule-based data selection for large language models.

Data-adaptive Safety Rules for Training Reward Models Rule-based data selection for large language models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.170124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2119d49-2202-4e31-b9a1-0c82e0ae652b · outbound

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

Data-adaptive Safety Rules for Training Reward Models Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.174468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60177fe9-4da5-4bc5-9d79-4b58bed8ef16 · outbound

This paper cites Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown.

Data-adaptive Safety Rules for Training Reward Models Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.179261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80ece55a-59bb-4ec9-ac52-06f13615a23a · outbound

This paper cites Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization.

Data-adaptive Safety Rules for Training Reward Models Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.188226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98c4542a-fc8f-46fe-a415-90a40a27d33f · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

Data-adaptive Safety Rules for Training Reward Models Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.193055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a34b5fb-7a42-4c67-b238-2a08df5dd680 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Data-adaptive Safety Rules for Training Reward Models LLaMA: Open and Efficient Foundation Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.197665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 589cc8e1-0d44-499e-99c3-9300818f6f27 · outbound

This paper cites Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts.

Data-adaptive Safety Rules for Training Reward Models Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.202305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15725ff4-32ee-4da2-80d6-910a317613ff · outbound

This paper cites HelpSteer2: Open-source dataset for training top-performing reward models.

Data-adaptive Safety Rules for Training Reward Models HelpSteer2: Open-source dataset for training top-performing reward models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.206994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a44391cd-317e-447f-a0d8-44b23ac6a679 · outbound

This paper cites SafetyBench: Evaluating the Safety of Large Language Models.

Data-adaptive Safety Rules for Training Reward Models SafetyBench: Evaluating the Safety of Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.211691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c4d6ac4-34cb-4be4-85e9-df16ad2ca076 · outbound

This paper cites − X t P+(t) logP+(t) # + 1 2.

Data-adaptive Safety Rules for Training Reward Models − X t P+(t) logP+(t) # + 1 2

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:25:13.788799Z

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 e82345c2-ad06-45c2-b429-4143a1f3a7b1 · outbound

This paper cites 16 Proof of Theorem 3.4.

Data-adaptive Safety Rules for Training Reward Models 16 Proof of Theorem 3.4

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:25:13.771723Z

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 f9badda7-99c6-439c-8cfb-18042465e3b4 · outbound

This paper cites Results are averaged over 2 trained models with different random seeds for optimal hyperparameter selection.

Data-adaptive Safety Rules for Training Reward Models Results are averaged over 2 trained models with different random seeds for optimal hyperparameter selection

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:25:13.741166Z

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 2d4d4fd1-2249-4b0a-836a-59f9ed0a4bb3 · outbound

This paper cites Specific versus General Principles for Constitutional AI.

Data-adaptive Safety Rules for Training Reward Models Specific versus General Principles for Constitutional AI

Reference 1951

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.160754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8552f2a-d285-4119-a6c9-ee9beb47689c · outbound

This paper cites Language Models are Few-Shot Learners.

Data-adaptive Safety Rules for Training Reward Models Language Models are Few-Shot Learners

Reference 1952

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.108657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0689ef8-c045-44ef-a253-98bd8de39d5f · outbound

This paper cites Llama 3.2: Revolutionizing edge ai and vision with open, customizable models.

Data-adaptive Safety Rules for Training Reward Models Llama 3.2: Revolutionizing edge ai and vision with open, customizable models

Reference 1975

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.183662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba69f6bc-1fa7-4417-837c-fa5160970cdd · outbound

This paper cites The Llama 3 Herd of Models.

Data-adaptive Safety Rules for Training Reward Models The Llama 3 Herd of Models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.123550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88c204dd-5cdf-441e-b506-db0b9521d109 · outbound

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

Data-adaptive Safety Rules for Training Reward Models Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.103534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5ed5287-008a-404d-ba01-f8b749518143 · outbound

This paper cites Qwen Technical Report.

Data-adaptive Safety Rules for Training Reward Models Qwen Technical Report

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-10T14:25:13.098361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 433e024a-c09c-44cd-898b-c5318d5171dc · outbound

This paper cites Llama 3.2: Advancing ai on edge and mobile devices.

Data-adaptive Safety Rules for Training Reward Models Llama 3.2: Advancing ai on edge and mobile devices

Reference 2025

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:25:13.832460Z

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.

Pith citing papers

Observation 5d6ef36b-588b-4687-8898-ad4c1ce30ca2 · inbound

MedGUIDE: Benchmarking Clinical Decision-Making in Large Language Models cites this paper.

MedGUIDE: Benchmarking Clinical Decision-Making in Large Language Models Data-adaptive Safety Rules for Training Reward Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T20:56:15.621439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69708228-e735-41ca-9311-dc586d66fc1f · inbound

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary cites this paper.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Data-adaptive Safety Rules for Training Reward Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:27.438057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26cf5ff7-62cf-458f-8a51-58f0d698fee8 · inbound

Automating SKILL.md Generation for Computer-Using Agents via Interaction Trajectory Mining cites this paper.

Automating SKILL.md Generation for Computer-Using Agents via Interaction Trajectory Mining Data-adaptive Safety Rules for Training Reward Models

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-07-04T04:19:34.992897Z

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.