Pith. sign in

Paper Citation Record · LEDGER

Position: Editing Large Language Models Poses Serious Safety Risks

As of 9 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 1 inbound Pith citation observation for arXiv:2502.02958.

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

pith.paper-citation-record.v1
2502.02958 v3

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T10:32:31.366415Z

measured 21 of 21 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:51:54.491362Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T11:51:55.251367Z

Reference resolution

20 of 20 outbound references displayed

  • verified exact0
  • verified fuzzy3
  • unresolved16
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation fc024716-1605-4e17-84bb-2689bac9f8b3 · outbound

This paper cites The Llama 3 Herd of Models.

Position: Editing Large Language Models Poses Serious Safety Risks The Llama 3 Herd of Models

Reference 2

Resolution
malformed identifier
no resolver link, observed 2026-08-09T10:32:31.262254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T10:32:31.262254Z digest=sha256:074dbf52a2d8444dff9070ae3115e715922ffb9965ae4dc02a337fe1339de744

Observation a740e17a-ade1-44e2-8e7d-5604360ec1b0 · outbound

This paper cites URL https://bera-journals.onlinelibrary.

Position: Editing Large Language Models Poses Serious Safety Risks URL https://bera-journals.onlinelibrary

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-09T10:32:31.302241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T10:32:31.302241Z digest=sha256:0013b7c1e6542c4ee8667614452a0622c60f43b82217c1a1723c08a7fc791ffd

Observation bd1cdebf-b555-411b-8754-01fbbfc1c1a1 · outbound

This paper cites Enhancing Data Privacy in Large Language Models through Private Association Editing.

Position: Editing Large Language Models Poses Serious Safety Risks Enhancing Data Privacy in Large Language Models through Private Association Editing

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-09T10:32:31.329825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T10:32:31.329825Z digest=sha256:25e56a76e4a7e52b95df89e936e82fdb2b00e750b6acd3b1c46becddaeba823c

Observation 13b98922-9f3d-4199-81fc-70a598c6fe46 · outbound

This paper cites The Rise and Potential of Large Language Model Based Agents: A Survey.

Position: Editing Large Language Models Poses Serious Safety Risks The Rise and Potential of Large Language Model Based Agents: A Survey

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-09T10:32:31.340388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T10:32:31.340388Z digest=sha256:9e572508121c9b60b0141ef54e7a031551d46ff30195620450091dcac83d3aab

Observation 0b9b8b54-a29f-4226-812d-fdfb12ec3cc4 · outbound

This paper cites MEGen: Generative Backdoor into Large Language Models via Model Editing.

Position: Editing Large Language Models Poses Serious Safety Risks MEGen: Generative Backdoor into Large Language Models via Model Editing

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-09T10:32:31.313592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T10:32:31.313592Z digest=sha256:d2832065bf9924456d3fa4e084f6634996fd1b71fe1bea8499cfa8ae4180cc4a

Observation eabfe1c5-ffb6-4407-82ef-28a4658de053 · outbound

This paper cites acl-short.107/.

Position: Editing Large Language Models Poses Serious Safety Risks acl-short.107/

Reference 107

Resolution
unresolved
no resolver link, observed 2026-08-09T10:32:31.356269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T10:32:31.356269Z digest=sha256:f6a3d58cf7c0eb3ed6b56967e092545c77edc813bec9031f0b5ef1aa8808dc4e

Observation f35ccd45-eeb5-4474-ad8d-ff1094758210 · outbound

This paper cites findings-emnlp.236/.

Position: Editing Large Language Models Poses Serious Safety Risks findings-emnlp.236/

Reference 236

Resolution
unresolved
no resolver link, observed 2026-08-09T10:32:31.345719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T10:32:31.345719Z digest=sha256:0e9eba510812eb1ec6a1959f4fd763ebe97deeed26d2d7970ee44c33b536a5f1

Observation c8d060eb-c0cb-44da-8302-806da5226062 · outbound

This paper cites Identifying Knowledge Editing Types in Large Language Models.

Position: Editing Large Language Models Poses Serious Safety Risks Identifying Knowledge Editing Types in Large Language Models

Reference 243

Resolution
unresolved
no resolver link, observed 2026-08-09T10:32:31.308082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T10:32:31.308082Z digest=sha256:08f1f954d799fc600ebe93b07cd1b71f898621a13bf59dfe47a8967116108bff

Observation 5a34ad55-e252-47fc-b686-c0dc6729bfc8 · outbound

This paper cites findings-emnlp.273/.

Position: Editing Large Language Models Poses Serious Safety Risks findings-emnlp.273/

Reference 273

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T10:32:31.669382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-09T10:32:31.324613Z digest=sha256:4b22c2510a3718247263c0773369d44da29ccc455a5e768cb4fd04da153f4fed

Observation 783e3167-b4b5-4929-a306-2df5e81d14ad · outbound

This paper cites findings-emnlp.293/.

Position: Editing Large Language Models Poses Serious Safety Risks findings-emnlp.293/

Reference 293

Resolution
unresolved
no resolver link, observed 2026-08-09T10:32:31.361165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T10:32:31.361165Z digest=sha256:78f24bdfb43a7266993f0687eb41e844b7cc78229366e879cd0605887b6a56e6

Observation 46ba0a62-6f2f-4291-ad29-71f53b28a0f5 · outbound

This paper cites emnlp-main.296/.

Position: Editing Large Language Models Poses Serious Safety Risks emnlp-main.296/

Reference 296

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T10:32:31.650721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-09T10:32:31.366415Z digest=sha256:e84895c5d77dd19a229fb36e339394f642ff121a1bea98a94736ef6adae4469a

Observation 20badddf-6b41-47c0-8e9c-80f5b527f511 · outbound

This paper cites acl-long.378/.

Position: Editing Large Language Models Poses Serious Safety Risks acl-long.378/

Reference 378

Resolution
unresolved
no resolver link, observed 2026-08-09T10:32:31.268441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T10:32:31.268441Z digest=sha256:119d66d0a21d07cc65920d174b35581be6296e7a41961f14bdd1b881e21c939c

Observation 7b8b6718-cdf5-45b6-8aee-52c62413604c · outbound

This paper cites findings-acl.421/.

Position: Editing Large Language Models Poses Serious Safety Risks findings-acl.421/

Reference 421

Resolution
unresolved
no resolver link, observed 2026-08-09T10:32:31.319301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T10:32:31.319301Z digest=sha256:9b5413bb3e5d50f4410f64db758765e54cac262ce72b4162d343d5ea108c19ad

Observation bdbfe414-168a-4b1a-82fa-e76841451487 · outbound

This paper cites findings-emnlp.469/.

Position: Editing Large Language Models Poses Serious Safety Risks findings-emnlp.469/

Reference 469

Resolution
unresolved
no resolver link, observed 2026-08-09T10:32:31.335138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T10:32:31.335138Z digest=sha256:16abbac4274230fec944ab57ab69e977d713215a35e14ec8ac427bad3aa21cc0

Observation 28dbc81b-9e99-4d97-933e-e2a3ee3a83f5 · outbound

This paper cites emnlp-main.764/.

Position: Editing Large Language Models Poses Serious Safety Risks emnlp-main.764/

Reference 764

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T10:32:31.687059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=pdf_text observed=2026-08-09T10:32:31.297069Z digest=sha256:8f6798da852b27a01c6d39eba965dabbc4bd1950ab2f2d7af43459b41264601f

Observation 697760be-d05d-497f-8dd7-b8b10b0bb6f2 · outbound

This paper cites findings-emnlp.903/.

Position: Editing Large Language Models Poses Serious Safety Risks findings-emnlp.903/

Reference 903

Resolution
unresolved
no resolver link, observed 2026-08-09T10:32:31.284782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T10:32:31.284782Z digest=sha256:7015eea54205f3f1c91aeede5f9599b1447d07a7861a5110f28071d714396526

Observation 2e6d0833-213e-4406-9487-fe3a4ac9d5e2 · outbound

This paper cites A Comprehensive Study of Knowledge Editing for Large Language Models.

Position: Editing Large Language Models Poses Serious Safety Risks A Comprehensive Study of Knowledge Editing for Large Language Models

Reference 1043

Resolution
unresolved
no resolver link, observed 2026-08-09T10:32:31.351008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T10:32:31.351008Z digest=sha256:0c18886d8c3b0e3dae8854062f76409bdecaaf41d6b99af68954c2ccf3e48c0d

Observation a6281ed4-3885-466d-8913-011200bbf4ba · outbound

This paper cites emnlp-main.1210/.

Position: Editing Large Language Models Poses Serious Safety Risks emnlp-main.1210/

Reference 1210

Resolution
unresolved
no resolver link, observed 2026-08-09T10:32:31.273814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T10:32:31.273814Z digest=sha256:f45b1c29ae4e8c0e4ed7af4f0593aa438cab9cfdea4962bdb0714711d3d01891

Observation 043ce767-ce13-4e86-bc77-bef8d13968b9 · outbound

This paper cites Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communities.

Position: Editing Large Language Models Poses Serious Safety Risks Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communities

Reference 2022

Resolution
unresolved
no resolver link, observed 2026-08-09T10:32:31.291443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T10:32:31.291443Z digest=sha256:85455ec7ba08dd370a1bfae9342970571de1062b8955cc89ff76e7ab2c4c981a

Observation 23f5f2a8-681e-4856-bfbe-e0bae8a3b318 · outbound

This paper cites Accessed: 2025-01-30.

Position: Editing Large Language Models Poses Serious Safety Risks Accessed: 2025-01-30

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-09T10:32:31.256004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T10:32:31.256004Z digest=sha256:69d9a1f5f445512e458af4380da923fb8fa1daa076f1bddbd46210272f665790

Pith citing papers

Observation 7290928f-4e26-4d5d-a66e-63c19beb25be · inbound

Detoxification of Large Language Models through Output-layer Fusion with a Calibration Model cites this paper.

Detoxification of Large Language Models through Output-layer Fusion with a Calibration Model Position: Editing Large Language Models Poses Serious Safety Risks

Reference 47

Resolution
verified exact
local_arxiv, observed 2026-08-07T11:51:55.414117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

source=arxiv_source observed=2026-08-07T11:51:54.491362Z digest=sha256:4d765ac6333b99e00061eabe4d89c24047f931294872aefbd75f72237bcd628b