Paper Citation Record · LEDGER

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency

As of 8 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 1 inbound Pith citation observation for arXiv:2506.17209.

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

pith.paper-citation-record.v1
2506.17209 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T23:33:41.564268Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-15T02:09:42.090550Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-15T02:13:31.259656Z

Reference resolution

37 of 37 outbound references displayed

verified exact0
verified fuzzy0
unresolved36
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e71036ff-007a-4c22-9b98-d9fb0db0a245 · outbound

This paper cites MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notes.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T23:33:36.756665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0146a7af-abd5-4d0a-9425-19f4d1d0f852 · outbound

This paper cites an unresolved cited work.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T23:33:36.898870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c7b2641-7e21-44d8-96c1-d665a31333cd · outbound

This paper cites LLM-Safety Evaluations Lack Robustness.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency LLM-Safety Evaluations Lack Robustness

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T23:33:37.087798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfdd60c7-a227-426c-b8e7-eab1869d55da · outbound

This paper cites an unresolved cited work.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:33:46.018491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f5759a1e-5122-4f47-94ed-a4b448e293a5 · outbound

This paper cites Scaling Trends for Data Poisoning in LLMs.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Scaling Trends for Data Poisoning in LLMs

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T23:33:37.343089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4827cc4d-0a7d-48eb-b251-40b6d75a5e53 · outbound

This paper cites an unresolved cited work.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:33:45.761039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 365f494f-40fc-4303-bdeb-a4b1298de98c · outbound

This paper cites an unresolved cited work.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T23:33:37.597429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb9d59a8-1d3b-4ce9-9a36-6aa7382b6b2d · outbound

This paper cites an unresolved cited work.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:33:45.438474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 640846a5-1e1f-43e8-9f63-7e62be45986c · outbound

This paper cites an unresolved cited work.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:33:45.233726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 56ad4904-6ddc-4818-983f-65e468aaaee7 · outbound

This paper cites an unresolved cited work.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:33:44.962163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 303c1bc1-8ed6-4754-866f-ec47c45f6918 · outbound

This paper cites an unresolved cited work.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:33:44.653032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7bd952c3-2d47-472a-bf59-ff037ce163f8 · outbound

This paper cites an unresolved cited work.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:33:44.424214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 076433ab-6861-4243-b4f2-0040596c2efa · outbound

This paper cites Fine-Tuning, Quantization, and LLMs: Navigating Unintended Outcomes.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Fine-Tuning, Quantization, and LLMs: Navigating Unintended Outcomes

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T23:33:38.401901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad933c1b-7a01-4ba1-8ed3-cb314ddb6a47 · outbound

This paper cites LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T23:33:38.516672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87835160-6169-4bad-85ab-42d70d58e263 · outbound

This paper cites Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T23:33:38.666517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5963e83d-331e-42b7-bcca-cc2dc8b349fb · outbound

This paper cites an unresolved cited work.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:33:44.251244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 259050c1-f68e-4eee-bcfe-eaa5b330b5ab · outbound

This paper cites an unresolved cited work.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T23:33:38.930380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c00da5a3-36ef-4978-bec9-a06271de5637 · outbound

This paper cites Goal-Oriented Prompt Attack and Safety Evaluation for LLMs.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Goal-Oriented Prompt Attack and Safety Evaluation for LLMs

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T23:33:39.030025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf9f6ca6-6fad-4fad-9587-bdaf03139174 · outbound

This paper cites an unresolved cited work.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:33:43.996741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d5edf85e-a2e6-4127-b43c-e36dc4f4ac52 · outbound

This paper cites an unresolved cited work.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Unresolved cited work

Reference 20

Resolution: metadata mismatch; raw_fallback, observed 2026-08-06T23:33:42.104507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 12857be6-f533-4fe5-8d96-830edcc36f21 · outbound

This paper cites an unresolved cited work.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:33:43.809732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d4b10d0d-c803-44c1-bf08-f2c54490e87a · outbound

This paper cites an unresolved cited work.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:33:43.558277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c8df74bc-a353-499f-9f1b-157b364ab88a · outbound

This paper cites an unresolved cited work.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:33:43.317975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a8119829-5314-4a17-964b-2f11f534b109 · outbound

This paper cites an unresolved cited work.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:33:43.084294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a8778340-3b0d-4dec-b31e-c5a21a7e5752 · outbound

This paper cites Safety Assessment of Chinese Large Language Models.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Safety Assessment of Chinese Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T23:33:39.890116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e25d0d39-a476-4383-b5cc-3cc6707937bc · outbound

This paper cites Hashimoto.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Hashimoto

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T23:33:40.046677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb0a79c2-36d6-4e7c-a4e3-c03104141af9 · outbound

This paper cites Introducing v0.5 of the AI Safety Benchmark from MLCommons.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Introducing v0.5 of the AI Safety Benchmark from MLCommons

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T23:33:40.156057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f83ef09f-72de-4e00-92e2-0405adcdb8d1 · outbound

This paper cites SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T23:33:40.319869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d18de42-b578-4d03-b7bd-395ff36e09a0 · outbound

This paper cites an unresolved cited work.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T23:33:40.452913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5253c95-d6b6-4923-a35c-75abcbb43a0c · outbound

This paper cites an unresolved cited work.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T23:33:40.638535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43b079be-3979-4d21-bdaa-933efacbd9cf · outbound

This paper cites an unresolved cited work.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:33:42.800142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0247c5b9-f005-42d1-a98a-a103fff62eba · outbound

This paper cites SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T23:33:40.895794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 574b4f9d-c622-4a9a-873a-34bff906c65b · outbound

This paper cites Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T23:33:41.022429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee715005-0d44-4384-b381-7030e1601266 · outbound

This paper cites an unresolved cited work.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-06T23:33:42.541060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0c635277-4177-47f6-b1a9-88ed869b2363 · outbound

This paper cites JADE: A Linguistics-based Safety Evaluation Platform for Large Language Models.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency JADE: A Linguistics-based Safety Evaluation Platform for Large Language Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T23:33:41.302545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f93b40bb-bd9d-4356-b5cb-4b13639ac9f7 · outbound

This paper cites online" 'onlinestring :=.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency online" 'onlinestring :=

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T23:33:41.427806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89fd420b-ad64-4282-bfc7-68d3ae3ee39d · outbound

This paper cites write newline.

Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency write newline

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T23:33:41.564268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 2733e459-27d7-415b-afb1-8cfdff86dc90 · inbound

The Great Pretender: A Stochasticity Problem in LLM Jailbreak cites this paper.

The Great Pretender: A Stochasticity Problem in LLM Jailbreak Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-15T02:13:31.261167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.