Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-05T22:21:39.095042Z
Paper Citation Record · LEDGER
Gradient Surgery for Safe LLM Fine-Tuning
As of 19 August 2026, this Paper Citation Record lists 2 of 2 outbound references and 4 inbound Pith citation observations for arXiv:2508.07172.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-07-13T12:04:13.336341Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-07-01T21:56:15.987326Z
Reference resolution
2 of 2 outbound references displayed
- verified exact0
- verified fuzzy0
- unresolved2
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 69cd2309-9341-4780-a8a3-bd57cb76bb36 · outbound
This paper cites SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging.
Gradient Surgery for Safe LLM Fine-Tuning SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging
Reference 2021
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T22:21:39.095042Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6c03869a-dafc-476d-86aa-c11aebb3b08c · outbound
This paper cites Training Verifiers to Solve Math Word Problems.
Gradient Surgery for Safe LLM Fine-Tuning Training Verifiers to Solve Math Word Problems
Reference 2024
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T22:21:39.091517Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
Observation b47801cc-3742-469e-a375-0b68f43005aa · inbound
CURE:Circuit-Aware Unlearning for LLM-based Recommendation cites this paper.
CURE:Circuit-Aware Unlearning for LLM-based Recommendation Gradient Surgery for Safe LLM Fine-Tuning
Reference 38
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T16:48:02.737914Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation 0b2cdec6-439c-4560-804c-270d90524470 · inbound
A Numerical PDEs Approach to Evolution Equations in Shape Analysis Based on Regularized Morphoelasticity cites this paper.
A Numerical PDEs Approach to Evolution Equations in Shape Analysis Based on Regularized Morphoelasticity Gradient Surgery for Safe LLM Fine-Tuning
Reference 38
- Resolution
- unresolved
- no resolver link, observed 2026-07-13T12:04:13.336341Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c0b18a71-6e69-46ef-aa2a-bb87d47ea228 · inbound
SPARD: Defending Harmful Fine-Tuning Attack via Safety Projection with Relevance-Diversity Data Selection cites this paper.
SPARD: Defending Harmful Fine-Tuning Attack via Safety Projection with Relevance-Diversity Data Selection Gradient Surgery for Safe LLM Fine-Tuning
Reference 18
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-06-29T13:53:28.675623Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.
Observation eb57267f-6efd-4f4e-a55c-dc5f489e2acc · inbound
Two to Tango: Coupled Task-Reference Selection for Safe LLM Fine-tuning cites this paper.
Two to Tango: Coupled Task-Reference Selection for Safe LLM Fine-tuning Gradient Surgery for Safe LLM Fine-Tuning
Reference 9
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T21:56:15.989152Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.