Paper Citation Record · LEDGER

GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO

As of 8 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 0 inbound Pith citation observations for arXiv:2506.08965.

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

pith.paper-citation-record.v1
2506.08965 v1

Coverage vector

measured 13 of 13 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:03:59.969588Z

measured 13 of 13 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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

13 of 13 outbound references displayed

verified exact0
verified fuzzy5
unresolved8
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 03fe4b88-0c49-479c-a137-bec123b343a1 · outbound

This paper cites an unresolved cited work.

GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:04:00.872967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 76d43501-a5be-4718-a772-01626ecea597 · outbound

This paper cites strong signal.

GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO strong signal

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:04:00.712230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 45c4b94b-5f19-4f9b-8836-fea49deded49 · outbound

This paper cites Weak Accept or Strong Reject vs.

GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO Weak Accept or Strong Reject vs

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:04:00.271775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e7bb3a19-2414-47b3-bf2d-6a8c61a5c1b6 · outbound

This paper cites Generative Reward Models.

GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO Generative Reward Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:59.316747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0346ca06-8dc5-42b6-8bac-5b01371268fd · outbound

This paper cites Beyond Scalar Reward Model: Learning Generative Judge from Preference Data.

GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO Beyond Scalar Reward Model: Learning Generative Judge from Preference Data

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:59.531765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6921bfe3-fb3a-4a1c-9b50-f04875cc2178 · outbound

This paper cites The model thus converges to an optimal solu- tion consistent with the true preference order- ing (up to an additive scaling).

GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO The model thus converges to an optimal solu- tion consistent with the true preference order- ing (up to an additive scaling)

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:04:00.559616Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0d90e109-0ec1-4a4d-a75e-8c517cb91d5b · outbound

This paper cites This retains the positive gradient properties 14 of logistic log-likelihood, allowing standard optimizers to converge efficiently.

GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO This retains the positive gradient properties 14 of logistic log-likelihood, allowing standard optimizers to converge efficiently

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:04:00.426144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7e971c68-9613-45c3-98c3-6249acb37590 · outbound

This paper cites Proximal Policy Optimization Algorithms.

GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO Proximal Policy Optimization Algorithms

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:59.448741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93599e44-d838-4697-8c2d-62358cf345b5 · outbound

This paper cites Training Deep Nets with Sublinear Memory Cost.

GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO Training Deep Nets with Sublinear Memory Cost

Reference 1992

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:59.265968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a49f408-87ef-4be4-8efc-4928a420e7ba · outbound

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

GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO A General Language Assistant as a Laboratory for Alignment

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:59.109692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c48772e5-ded9-4861-8e38-87baf9bd560c · outbound

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

GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO Training language models to follow instructions with human feedback

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:59.185692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98fe3752-c817-4a50-880f-dea6985cabb7 · outbound

This paper cites Samyam Rajbhandari, Jeff Rasley, Olatunji Ruwase, and Yuxiong He.

GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO Samyam Rajbhandari, Jeff Rasley, Olatunji Ruwase, and Yuxiong He

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:04:01.019646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 717b82e3-abeb-4939-8f27-cbe14a2d3d99 · outbound

This paper cites Critique-out-Loud Reward Models.

GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO Critique-out-Loud Reward Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:59.046421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.