Pith. sign in

Paper Citation Record · LEDGER

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack

As of 10 August 2026, this Paper Citation Record lists 17 of 17 outbound references and 0 inbound Pith citation observations for arXiv:2606.05614.

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

pith.paper-citation-record.v1
2606.05614 v1

Coverage vector

measured 17 of 17 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-28T01:59:37.573954Z

measured 17 of 17 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+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

17 of 17 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved13
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch4

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7a186941-52c9-49f1-8fcd-d53f1428acc9 · outbound

This paper cites InR0-F oMo:Robustness of Few- shot and Zero-shot Learning in Large F oundation Models.

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack InR0-F oMo:Robustness of Few- shot and Zero-shot Learning in Large F oundation Models

Reference 1

Resolution
unresolved
no resolver link, observed 2026-06-28T01:59:37.573954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T01:59:37.573954Z digest=sha256:3bf5d320dc7907954a1fd93618ed8c19a286ae60c1c97c027e5c149f727ce52a

Observation bd54d6db-fc97-4051-ac3d-ae54e13d8632 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack Training Verifiers to Solve Math Word Problems

Reference 2

Resolution
metadata mismatch
local_arxiv, observed 2026-07-02T12:36:56.921743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-06-28T01:59:37.573954Z digest=sha256:c2df91872c9da27bbe15fb42993f498622d6a9fab4bb60ba819cb594a00c36d3

Observation 860388ff-b06c-4311-bb65-4176bf47dbcb · outbound

This paper cites The Llama 3 Herd of Models.

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack The Llama 3 Herd of Models

Reference 3

Resolution
metadata mismatch
local_arxiv, observed 2026-07-02T12:36:56.927397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-06-28T01:59:37.573954Z digest=sha256:9571b6ff4c0d8bc460f9612ff05ce10689134f187f92c2a56e82d30aaf580ea1

Observation 510c11fa-a29b-49bb-a68a-4717cf35a180 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack Measuring Massive Multitask Language Understanding

Reference 4

Resolution
metadata mismatch
local_arxiv, observed 2026-07-02T12:36:56.924885Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-06-28T01:59:37.573954Z digest=sha256:c565c6163197f5d842b992cb5a916e238d15c616aa84c48d87ced23ba276120a

Observation 769321d3-7363-4023-a416-b65a0668cf49 · outbound

This paper cites GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher.

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Reference 5

Resolution
metadata mismatch
arxiv_id, observed 2026-07-02T12:36:56.906206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-06-28T01:59:37.573954Z digest=sha256:d09b69d26629049b5d3b949b4a61a4f103fd8d442b79e62635524ea2f47e4f01

Observation 5b13eb0f-2d3c-417e-9ca1-6c5409cfb38a · outbound

This paper cites Dataset informa- tion is detailed in Table 6.

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack Dataset informa- tion is detailed in Table 6

Reference 6

Resolution
unresolved
no resolver link, observed 2026-06-28T01:59:37.573954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T01:59:37.573954Z digest=sha256:7acbc562a3748aa8484fd708a4d8969d7157669ecfc80f46c1598108b1b43540

Observation a14259b3-5ed0-482e-a1b1-3c21c58b4b68 · outbound

This paper cites You are a helpful assistant.

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack You are a helpful assistant

Reference 7

Resolution
unresolved
no resolver link, observed 2026-06-28T01:59:37.573954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T01:59:37.573954Z digest=sha256:3c8340cb14b1406a7d4fafa14fecae8d4f207cbe9bd9b0c91b6026aa43096b6e

Observation fb03a38a-812e-415c-8054-e40dc8df8075 · outbound

This paper cites an unresolved cited work.

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack Unresolved cited work

Reference 8

Resolution
unresolved
no resolver link, observed 2026-06-28T01:59:37.573954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T01:59:37.573954Z digest=sha256:cb9008627a8eab4c48eae0ab20dbad040386d3f255e2e6107e12e38abb95142d

Observation 7f2d01fc-91c4-4cb4-826c-80141e8f392f · outbound

This paper cites an unresolved cited work.

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack Unresolved cited work

Reference 9

Resolution
unresolved
no resolver link, observed 2026-06-28T01:59:37.573954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T01:59:37.573954Z digest=sha256:aa41d9a71d3beadbc6c73695519a5b545682b0c46bf9059cec51824458ad62d1

Observation e2bf8b66-d10b-4c51-acde-1c876352f9e7 · outbound

This paper cites an unresolved cited work.

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack Unresolved cited work

Reference 10

Resolution
unresolved
no resolver link, observed 2026-06-28T01:59:37.573954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T01:59:37.573954Z digest=sha256:7efc8014df4e942a53d539f10678e033653c4f2d754d2f13f1a0625cb47066a5

Observation 37877cc7-8bb5-4991-9ba4-04f70d940d69 · outbound

This paper cites an unresolved cited work.

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack Unresolved cited work

Reference 11

Resolution
unresolved
no resolver link, observed 2026-06-28T01:59:37.573954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T01:59:37.573954Z digest=sha256:1ada55d698cc4d7c260d6a876ba645d7b0db9931fc3ed1feec818b86a8b95043

Observation 6e0ba482-b878-45f8-838d-5e3755617608 · outbound

This paper cites Yes" - meaning it would be classified as an instance of the behavior.

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack Yes" - meaning it would be classified as an instance of the behavior

Reference 12

Resolution
unresolved
no resolver link, observed 2026-06-28T01:59:37.573954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T01:59:37.573954Z digest=sha256:94cd2edcca3c0c5016a17e802c234f441d6a62a79366c2fe66abc9ba2b1097e9

Observation 7c0f3ca8-a570-486a-bcf0-f73f332ee161 · outbound

This paper cites an unresolved cited work.

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack Unresolved cited work

Reference 13

Resolution
unresolved
no resolver link, observed 2026-06-28T01:59:37.573954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T01:59:37.573954Z digest=sha256:d04e139f63f5c37b361a503cba5e29a79f8b9d53fa51d2bd90becae0da8047e1

Observation 6cd910f3-5e44-4a43-bfd3-a301e4feb59f · outbound

This paper cites an unresolved cited work.

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack Unresolved cited work

Reference 14

Resolution
unresolved
no resolver link, observed 2026-06-28T01:59:37.573954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T01:59:37.573954Z digest=sha256:1723ffc2a5d84b2fc1394f188d6acf477c4fb1de8ebbfef4e89a937c6bcab1aa

Observation 0f93db41-f3b2-4155-b145-eff79127d64e · outbound

This paper cites an unresolved cited work.

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack Unresolved cited work

Reference 15

Resolution
unresolved
no resolver link, observed 2026-06-28T01:59:37.573954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T01:59:37.573954Z digest=sha256:68f19a138e08c2b7b2e776a4cdd5182e56c8fda0876237bdaab79d9f59d6fd17

Observation 4605c827-5316-4587-8ae0-c248f6bea72b · outbound

This paper cites an unresolved cited work.

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack Unresolved cited work

Reference 16

Resolution
unresolved
no resolver link, observed 2026-06-28T01:59:37.573954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T01:59:37.573954Z digest=sha256:6220c6a3be0f5c5f7e107331ecadbe894659ab64f8a8df41c2971cddbb574bb3

Observation 5b466e7a-8ac6-46a8-9c7c-1efeb9464499 · outbound

This paper cites We redacted the full response because of safety concerns.

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack We redacted the full response because of safety concerns

Reference 17

Resolution
unresolved
no resolver link, observed 2026-06-28T01:59:37.573954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T01:59:37.573954Z digest=sha256:55e74f75efb0142461f00d4d983afd11cfda2336fbd7356727dd13ec55499d28

Pith citing papers

No inbound Pith citation observations are available.