Paper Citation Record · LEDGER

Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models

As of 20 August 2026, this Paper Citation Record lists 8 of 8 outbound references and 0 inbound Pith citation observations for arXiv:2512.06899.

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

pith.paper-citation-record.v1
2512.06899 v2

Coverage vector

measured 8 of 8 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T18:08:07.645902Z

measured 8 of 8 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+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

8 of 8 outbound references displayed

verified exact0
verified fuzzy0
unresolved8
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 42d9b17d-854d-48f0-be65-90f1db645899 · outbound

This paper cites C - C” denotes the cosine similarity between clean samples, “P - P.

Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models C - C” denotes the cosine similarity between clean samples, “P - P

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T18:08:07.645902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87c1adf6-8bb0-4e4f-8cff-93eb0d45c3e8 · outbound

This paper cites InProceedings of the 13th International Workshop on Semantic Evaluation, pages 75–86.

Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models InProceedings of the 13th International Workshop on Semantic Evaluation, pages 75–86

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T18:08:07.526269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 680ba610-dad7-4b01-9447-52f6936411cf · outbound

This paper cites Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models.

Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T18:08:07.581777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d5e2166-b626-41b3-8b66-2149600fc23e · outbound

This paper cites BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain.

Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-03T18:08:07.257731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 398337f3-6305-43d7-8168-855e079b4514 · outbound

This paper cites RoBERTa: A Robustly Optimized BERT Pretraining Approach.

Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models RoBERTa: A Robustly Optimized BERT Pretraining Approach

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-03T18:08:07.354319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2aa591c-51e6-437b-964a-4abf1f5ed654 · outbound

This paper cites Marcos Zampieri, Shervin Malmasi, Preslav Nakov, Sara Rosenthal, Noura Farra, and Ritesh Kumar.

Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models Marcos Zampieri, Shervin Malmasi, Preslav Nakov, Sara Rosenthal, Noura Farra, and Ritesh Kumar

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-03T18:08:07.457461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bea9a26-ef70-4672-8d27-2553ece13955 · outbound

This paper cites IAG: Input-aware Backdoor Attack on VLM-based Visual Grounding.

Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models IAG: Input-aware Backdoor Attack on VLM-based Visual Grounding

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-03T18:08:07.307583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e0ce249-7c3a-4778-b286-f730e7d3e6c7 · outbound

This paper cites Backdoor Pre-trained Models Can Transfer to All.

Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models Backdoor Pre-trained Models Can Transfer to All

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-03T18:08:07.403705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.