Paper Citation Record · LEDGER

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling

As of 16 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 0 inbound Pith citation observations for arXiv:2608.02951.

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

pith.paper-citation-record.v1
2608.02951 v1

Coverage vector

measured 27 of 27 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T15:02:45.665708Z

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+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

27 of 27 outbound references displayed

verified exact1
verified fuzzy7
unresolved19
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ee422279-496a-4840-9e7d-bfb307e0ec00 · outbound

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

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T15:02:45.558196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d290f816-01cf-4562-8b67-462bbce1b352 · outbound

This paper cites Contrastive Preference Learning: Learning from Human Feedback without RL.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling Contrastive Preference Learning: Learning from Human Feedback without RL

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T15:02:45.577850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98b5c4aa-31eb-42e3-a4ba-65e39627fcad · outbound

This paper cites Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T15:02:45.582408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a480b73-c493-4684-92e3-dccca44d5ce0 · outbound

This paper cites RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T15:02:45.609451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f6a9377-259a-45e1-9173-21492ddfe58f · outbound

This paper cites Reinforcement Learning with Segment Feedback.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling Reinforcement Learning with Segment Feedback

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-08-15T15:02:45.752291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 605b043e-97f6-4fc4-89d8-ad25e4b7c7df · outbound

This paper cites Adam: A Method for Stochastic Optimization.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling Adam: A Method for Stochastic Optimization

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T15:02:45.622442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08c4f306-f481-4970-b9c9-d8c977c836e5 · outbound

This paper cites Decoupled Weight Decay Regularization.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling Decoupled Weight Decay Regularization

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T15:02:45.631715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e28fc222-6012-45fa-b84a-03663fb3c60f · outbound

This paper cites Approximating kl divergence, 2020.URL http://joschu.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling Approximating kl divergence, 2020.URL http://joschu

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:02:46.087144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4fb484bb-1eb7-4c64-a6d9-305513f72586 · outbound

This paper cites 15 A.2 Comparison of Preference Models.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling 15 A.2 Comparison of Preference Models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:02:46.071148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ba2a8584-11b2-422a-9c6f-84a761d8d5d0 · outbound

This paper cites This makes them inapplicable to many modern RL problems.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling This makes them inapplicable to many modern RL problems

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:02:46.055188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 13ac6ae2-d619-4207-9ba0-d10702023097 · outbound

This paper cites Specifically, even if the partial returns of two segments are the same, 15 humans could still prefer one trajectory segment based on the value of the last state and action.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling Specifically, even if the partial returns of two segments are the same, 15 humans could still prefer one trajectory segment based on the value of the last state and action

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:02:46.040674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 156a5eb1-7f77-42e1-b4bb-c7055b8afd38 · outbound

This paper cites During training, policies were Gaussian with a parameter controlling the log standard deviation for each dimension in the action space.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling During training, policies were Gaussian with a parameter controlling the log standard deviation for each dimension in the action space

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:02:46.010880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ff72a96f-415a-4d8e-9695-9a1ab3b7e032 · outbound

This paper cites The global gradient norm is clipped to1.0.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling The global gradient norm is clipped to1.0

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:02:45.996416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fe301495-77e8-4b26-9e33-1856d6f1db27 · outbound

This paper cites We observe that in Ant-v5 usingπθt´1 as the second policy out performs setting the second policy toπθref.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling We observe that in Ant-v5 usingπθt´1 as the second policy out performs setting the second policy toπθref

Reference 1000

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:02:46.025703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 34a6412f-ff93-4201-886c-6617e19fa7e0 · outbound

This paper cites Models of human preference for learning reward functions.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling Models of human preference for learning reward functions

Reference 1952

Resolution: unresolved; no resolver link, observed 2026-08-15T15:02:45.573168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14ed6ea2-811c-45d0-84b0-51b5553374de · outbound

This paper cites Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 2012

Resolution: unresolved; no resolver link, observed 2026-08-15T15:02:45.591812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ff964b8-3fa5-467a-8dfa-88ee91dd45af · outbound

This paper cites Proximal Policy Optimization Algorithms.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling Proximal Policy Optimization Algorithms

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-15T15:02:45.548076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52bf253f-7a60-4fdd-acb2-db84ff3810f2 · outbound

This paper cites Making Reinforcement Learning Work on Swimmer.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling Making Reinforcement Learning Work on Swimmer

Reference 2014

Resolution: unresolved; no resolver link, observed 2026-08-15T15:02:45.626921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 526c189c-caec-415d-a723-96ba1e20aceb · outbound

This paper cites PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-15T15:02:45.601173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 179e76b8-8da8-4c1f-8fe0-de3fa777a8c2 · outbound

This paper cites Aligning Text-to-Image Models using Human Feedback.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling Aligning Text-to-Image Models using Human Feedback

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-15T15:02:45.567940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0d7fa27-dac7-474f-9532-0b7e02d9daa7 · outbound

This paper cites Playing Atari with Deep Reinforcement Learning.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling Playing Atari with Deep Reinforcement Learning

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-15T15:02:45.542769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38abb7ee-237b-4218-993a-661c3d4087de · outbound

This paper cites Preference Transformer: Modeling Human Preferences using Transformers for RL.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling Preference Transformer: Modeling Human Preferences using Transformers for RL

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-15T15:02:45.613860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b85b8801-d6b7-4c14-a2b0-d595bc8b65a0 · outbound

This paper cites Gymnasium: A Standard Interface for Reinforcement Learning Environments.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling Gymnasium: A Standard Interface for Reinforcement Learning Environments

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-15T15:02:45.605223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea2ce2c8-9538-4056-8515-e1ea757041a9 · outbound

This paper cites RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-15T15:02:45.552796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 227b8e35-4610-4640-bc74-c6d145f81fd4 · outbound

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

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-15T15:02:45.563041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7f7b12a-67c5-4df6-b868-14f03998d776 · outbound

This paper cites Sign-SZPO: Provable Preference-based Reinforcement Learning with an Unknown Link Function.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling Sign-SZPO: Provable Preference-based Reinforcement Learning with an Unknown Link Function

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T15:02:45.587036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d978a87-4205-43fd-bd9a-0b116899fbf5 · outbound

This paper cites Direct Language Model Alignment from Online AI Feedback.

SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling Direct Language Model Alignment from Online AI Feedback

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-15T15:02:45.596461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.