Pith. sign in

Paper Citation Record · LEDGER

Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks

As of 11 August 2026, this Paper Citation Record lists 7 of 7 outbound references and 0 inbound Pith citation observations for arXiv:2511.13789.

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

pith.paper-citation-record.v1
2511.13789 v1

Coverage vector

measured 7 of 7 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-17T22:01:09.858921Z

measured 7 of 7 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+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

7 of 7 outbound references displayed

  • verified exact2
  • verified fuzzy2
  • unresolved1
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e361f2b7-4e76-4aab-9229-fb0bc13362a1 · outbound

This paper cites Mistral 7B.

Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks Mistral 7B

Reference 1

Resolution
metadata mismatch
local_arxiv, observed 2026-05-17T22:02:08.635939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-05-17T22:01:09.858921Z digest=sha256:90a7bad8394b591b19d12823aa266f2b24dc4fb34844041755d9786df5f9af6f

Observation bfd43c69-bec3-410e-a3a1-8d91b48713c3 · outbound

This paper cites A Study of the Attention Abnormality in Trojaned BERTs.

Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks A Study of the Attention Abnormality in Trojaned BERTs

Reference 2

Resolution
verified exact
arxiv_id, observed 2026-05-17T22:02:08.624740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-05-17T22:01:09.858921Z digest=sha256:4598a2942d2c76b9424ee548901bc3be60b6218521f7c497826179571ae5f149

Observation a77a443e-3dc9-448d-b01d-51f1f1d0589d · outbound

This paper cites OpenHowNet: An Open Sememe-based Lexical Knowledge Base.

Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks OpenHowNet: An Open Sememe-based Lexical Knowledge Base

Reference 3

Resolution
metadata mismatch
local_arxiv, observed 2026-05-17T22:02:08.632068Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-05-17T22:01:09.858921Z digest=sha256:745da8acba3b12a285569f2ee5e029a9e3139564654bc9d59e073e81719c8f96

Observation 62a5fc8b-95a8-434c-a918-a514f3b50bbe · outbound

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

Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models

Reference 4

Resolution
verified exact
arxiv_id, observed 2026-05-17T22:02:08.627638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-05-17T22:01:09.858921Z digest=sha256:47c7f879cb92542556f9c8ed7460b2978c942475debde91d561c5350d5c35125

Observation c00ebbf9-2c4d-4bdf-b5c2-bfc481a5a918 · outbound

This paper cites an unresolved cited work.

Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks Unresolved cited work

Reference 5

Resolution
unresolved
raw_fallback, observed 2026-05-17T22:02:09.306812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-05-17T22:01:09.858921Z digest=sha256:2295fdccf0fb4dd4bb65ecbd67d17bf5e7872d335285265a9e54b1aa9c5b8969

Observation e21b1552-cdc4-45e9-be28-2a1096de9c3c · outbound

This paper cites cf”, “mn.

Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks cf”, “mn

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-05-17T22:02:09.310943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-05-17T22:01:09.858921Z digest=sha256:d2ddc23bab8140a4d2bbd665c4ed0913d82e87283178d0d467a8089a557258c2

Observation ea693ed4-177a-469e-942a-40cfa6fc5942 · outbound

This paper cites The final PCA-reduced dimensionalityh i is set to 32.

Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks The final PCA-reduced dimensionalityh i is set to 32

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-05-17T22:02:09.308895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-05-17T22:01:09.858921Z digest=sha256:df9e570113b2f5f668a40e33f34deb3edd4fc393f6aad2b980d6b41df22ab67d

Pith citing papers

No inbound Pith citation observations are available.