Paper Citation Record · LEDGER

Debiasing Online Preference Learning via Preference Feature Preservation

As of 8 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 0 inbound Pith citation observations for arXiv:2506.11098.

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

pith.paper-citation-record.v1
2506.11098 v1

Coverage vector

measured 49 of 49 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T06:05:32.728004Z

measured 49 of 49 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 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

49 of 49 outbound references displayed

verified exact1
verified fuzzy0
unresolved48
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 97cd3f7b-566b-455b-9cdd-a3f0b49084f3 · outbound

This paper cites online" 'onlinestring :=.

Debiasing Online Preference Learning via Preference Feature Preservation online" 'onlinestring :=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T06:05:32.520994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c393ac49-6827-468f-9471-6b4e1b397011 · outbound

This paper cites write newline.

Debiasing Online Preference Learning via Preference Feature Preservation write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T06:05:32.526128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b14c64b4-b5fe-4978-a3d5-703f650aecdc · outbound

This paper cites write newline.

Debiasing Online Preference Learning via Preference Feature Preservation write newline

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T06:05:32.531806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a67aad3a-e58a-4e61-a615-7a741689fdc0 · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.532490Z

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 2acc3515-d81f-4cc2-8512-0b46352bdb5c · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.518687Z

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 44a430db-54fa-440b-b31f-c752a6d5620a · outbound

This paper cites A General Language Assistant as a Laboratory for Alignment.

Debiasing Online Preference Learning via Preference Feature Preservation A General Language Assistant as a Laboratory for Alignment

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T06:05:32.545630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54f27b40-29ad-4e25-8375-2ab3cc997f5a · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.504015Z

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 4638ed7e-9013-4d13-a010-f0d005282a97 · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T06:05:32.554671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fa1e298-330f-4b76-91a0-94a7d1af9242 · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.479058Z

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 39cd5008-b9f1-45cb-b3e0-b8c2368a4106 · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.466212Z

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 15bfb751-8677-430a-ba9e-c97906086dd8 · outbound

This paper cites UltraFeedback: Boosting Language Models with Scaled AI Feedback.

Debiasing Online Preference Learning via Preference Feature Preservation UltraFeedback: Boosting Language Models with Scaled AI Feedback

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T06:05:32.567554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37b32f76-af8f-48b6-844a-3ffdeb628b8b · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.452443Z

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 14915f7f-eb95-403e-91cc-6af505725a08 · outbound

This paper cites Enhancing Chat Language Models by Scaling High-quality Instructional Conversations.

Debiasing Online Preference Learning via Preference Feature Preservation Enhancing Chat Language Models by Scaling High-quality Instructional Conversations

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T06:05:32.576314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbe05557-40df-4a4b-a544-a963a7750947 · outbound

This paper cites RLHF Workflow: From Reward Modeling to Online RLHF.

Debiasing Online Preference Learning via Preference Feature Preservation RLHF Workflow: From Reward Modeling to Online RLHF

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T06:05:32.580792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67bf7084-0174-4fcb-99f5-a281574c56aa · outbound

This paper cites The Llama 3 Herd of Models.

Debiasing Online Preference Learning via Preference Feature Preservation The Llama 3 Herd of Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T06:05:32.585102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0209bffc-0395-4431-9978-bde3421de69e · outbound

This paper cites Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators.

Debiasing Online Preference Learning via Preference Feature Preservation Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T06:05:32.589245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec8188f9-2433-4f22-a2bf-cdf944df81a2 · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.438711Z

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 4a59ccb9-e276-465a-8636-d63bbbbe37c0 · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.425259Z

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 af5dfd71-9369-4733-ac9b-992386de1f21 · outbound

This paper cites Mistral 7B.

Debiasing Online Preference Learning via Preference Feature Preservation Mistral 7B

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T06:05:32.603244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df7810e6-6911-4b53-9744-df9bc024dc31 · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.412157Z

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 231ed846-a0a5-4267-8112-b3975ad68ce0 · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.399238Z

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 b44231d1-45fd-4c50-8cbb-88ba9410d503 · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.385631Z

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 2c603c55-2ae5-4eba-ab22-10ea4b4bced8 · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.372321Z

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 3955dbab-d44d-4b18-82f6-e7a3f4bea961 · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.358683Z

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 94169d60-021c-4f72-8000-9e67f334bd5d · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.343913Z

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 7c27b1ca-6f27-474e-8f27-021ee75597fa · outbound

This paper cites Dissecting Human and LLM Preferences.

Debiasing Online Preference Learning via Preference Feature Preservation Dissecting Human and LLM Preferences

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T06:05:32.631391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cd640aa-6fef-45cd-ab5a-98e22d37fa91 · outbound

This paper cites Decoupled Weight Decay Regularization.

Debiasing Online Preference Learning via Preference Feature Preservation Decoupled Weight Decay Regularization

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T06:05:32.635828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c8ed455-6fc1-4c28-9a79-47d7443ba863 · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.330752Z

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 0050e4e5-2c19-42df-b80a-5aefc823c192 · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 29

Resolution: verified exact; raw_fallback, observed 2026-08-07T06:05:33.018292Z

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 134dfb4e-b7b2-4554-a56a-0ec9ccb4fb01 · outbound

This paper cites GPT-4 Technical Report.

Debiasing Online Preference Learning via Preference Feature Preservation GPT-4 Technical Report

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T06:05:32.647804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d800e66-12e2-4516-a0b7-70f26436693b · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.316887Z

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 c16bedea-7899-4537-b161-7e33e1cf8054 · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.303371Z

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 e3c64ba8-a585-434f-8d09-81744b4e0b12 · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.289403Z

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 7ccfae8f-eb6d-4547-99b4-4b9439e73479 · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.275333Z

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 0449bcc5-cd22-43c8-8a98-5a9be9064e05 · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.262059Z

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 0fc2bec0-5495-40c1-a5e9-18cfb280fb3c · outbound

This paper cites Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences.

Debiasing Online Preference Learning via Preference Feature Preservation Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T06:05:32.672178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3844b5c-fc83-4018-b6a9-5f94054c4f26 · outbound

This paper cites A Long Way to Go: Investigating Length Correlations in RLHF.

Debiasing Online Preference Learning via Preference Feature Preservation A Long Way to Go: Investigating Length Correlations in RLHF

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T06:05:32.676825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1ca1cb8-b1c0-4130-afcc-3099e44ece02 · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.248054Z

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 0b4f36e2-831a-4a94-b610-5e9d3d917d0f · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.232005Z

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 362a54b7-755f-4ab6-b9d8-4a615b1153db · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Debiasing Online Preference Learning via Preference Feature Preservation Gemini: A Family of Highly Capable Multimodal Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T06:05:32.689590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 242ee8b0-5754-4c86-9e0e-6a9315e892ae · outbound

This paper cites Zephyr: Direct Distillation of LM Alignment.

Debiasing Online Preference Learning via Preference Feature Preservation Zephyr: Direct Distillation of LM Alignment

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T06:05:32.693883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdd9d55c-10bc-41fe-9be2-aeac5ce84b3b · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.218139Z

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 9192bb21-5105-4608-9b76-1f00beb25dc1 · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.202246Z

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 0d0b9669-c8b2-4b83-8629-aa35d4e4397f · outbound

This paper cites Self-Play Preference Optimization for Language Model Alignment.

Debiasing Online Preference Learning via Preference Feature Preservation Self-Play Preference Optimization for Language Model Alignment

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T06:05:32.707537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 944ea925-9df0-422d-bede-ecfb6cef2c23 · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 45

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.188133Z

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 8a00e02c-ef7c-4cd6-b98f-5b30ad389630 · outbound

This paper cites Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss.

Debiasing Online Preference Learning via Preference Feature Preservation Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T06:05:32.715738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9520ea74-8889-43c0-bd1b-372e99a61b44 · outbound

This paper cites SLiC-HF: Sequence Likelihood Calibration with Human Feedback.

Debiasing Online Preference Learning via Preference Feature Preservation SLiC-HF: Sequence Likelihood Calibration with Human Feedback

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T06:05:32.720004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bea02bf-8970-4335-b3c0-29668a3e6023 · outbound

This paper cites an unresolved cited work.

Debiasing Online Preference Learning via Preference Feature Preservation Unresolved cited work

Reference 48

Resolution: unresolved; raw_fallback, observed 2026-08-07T06:05:33.174460Z

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 385a7655-4429-4b52-86ac-4b787c317a94 · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

Debiasing Online Preference Learning via Preference Feature Preservation Fine-Tuning Language Models from Human Preferences

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T06:05:32.728004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.