Paper Citation Record · LEDGER

Gradient Imbalance in Direct Preference Optimization

As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2502.20847.

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

pith.paper-citation-record.v1
2502.20847 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 4 of 4 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 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T23:57:17.153493Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-29T12:33:24.381267Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation fcaf57f2-2694-489d-a4c9-634d7a450521 · inbound

Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewards cites this paper.

Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewards Gradient Imbalance in Direct Preference Optimization

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T23:57:17.153493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e6ae5c4-0872-4532-865d-9a2fbc70ce22 · inbound

Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance cites this paper.

Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance Gradient Imbalance in Direct Preference Optimization

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-05-15T03:19:43.006228Z

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 438c61d5-70c6-47a2-a157-7ed5675da6ff · inbound

AdaDPO: Self-Adaptive Direct Preference Optimization with Balanced Gradient Updates cites this paper.

AdaDPO: Self-Adaptive Direct Preference Optimization with Balanced Gradient Updates Gradient Imbalance in Direct Preference Optimization

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T12:33:24.382739Z

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 4b061c23-3988-42e5-b43c-950eb3aa9a92 · inbound

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift cites this paper.

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift Gradient Imbalance in Direct Preference Optimization

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T17:47:41.496853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.