Pith. sign in

Paper Citation Record · LEDGER

Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace

As of 23 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 5 inbound Pith citation observations for arXiv:2410.13910.

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

pith.paper-citation-record.v1
2410.13910 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 5 of 5 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T01:09:03.317297Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-22T20:32:04.731154Z

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 f1619324-bea2-4223-a0d5-0cd153366038 · inbound

Defending against Backdoor Attacks via Module Switching cites this paper.

Defending against Backdoor Attacks via Module Switching Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace

Reference 57

Resolution
verified exact
arxiv_id, observed 2026-05-22T20:32:04.732667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T20:28:24.169272Z digest=sha256:72ab07d1a0c9eef4b0dd11e679b5acc4d57c3f145e36b3381d13226e5a28f4c2

Observation 77f4fed0-f010-43d2-9b61-6b803f53eb7b · inbound

Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets cites this paper.

Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-16T01:09:03.317297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T01:09:03.317297Z digest=sha256:3a9b8d2b55c6e89127be22ada18a85de5ce2e0eabd6c90fe1ac93ece510e3029

Observation f151b568-8217-4b12-8117-9873201dc6ca · inbound

Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias cites this paper.

Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-07T06:00:51.922284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T06:00:51.922284Z digest=sha256:9ad29f3a0d9c94057394874506ad02d24cd1af3a5824ee5691cf51f0aaafa6da

Observation 7d6de590-cab9-4f55-b9d7-f468dee8ff7f · inbound

Unifying Adversarial Perturbation for Graph Neural Networks cites this paper.

Unifying Adversarial Perturbation for Graph Neural Networks Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-05T13:44:10.517845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T13:44:10.517845Z digest=sha256:a00b984ef03719fc580ce1600d2f16b5d621e560e87332fe95488e2c6c673501

Observation cc05a525-f187-4a51-91da-fc87494fd375 · inbound

When Skills Meet Safety: Benchmarking and Characterizing the Adaptive Jailbreak Robustness of Skill-Merged LLMs cites this paper.

When Skills Meet Safety: Benchmarking and Characterizing the Adaptive Jailbreak Robustness of Skill-Merged LLMs Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-14T04:46:16.009315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-14T04:46:16.009315Z digest=sha256:759c0011cd1ac3d853e812ba6462cee96a031b3f3fa2b4449da5e28ae616c6d4