Paper Citation Record · LEDGER

Towards medical AI misalignment: a preliminary study

As of 9 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2505.18212.

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

pith.paper-citation-record.v1
2505.18212 v1

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:52:17.039027Z

measured 31 of 31 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 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

31 of 31 outbound references displayed

verified exact1
verified fuzzy12
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9352bc8f-88eb-4d94-9ab0-317079dd4a2e · outbound

This paper cites Mistral Large system card, 2024.

Towards medical AI misalignment: a preliminary study Mistral Large system card, 2024

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:52:19.086894Z

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 ff977c06-a41e-472f-8c02-836e6d22019e · outbound

This paper cites Many-shot jailbreaking.

Towards medical AI misalignment: a preliminary study Many-shot jailbreaking

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:52:18.896857Z

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 7977d1d4-7841-4643-87d2-a3097260b1df · outbound

This paper cites LLMs Will Always Hallucinate, and We Need to Live With This.

Towards medical AI misalignment: a preliminary study LLMs Will Always Hallucinate, and We Need to Live With This

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T14:52:15.208059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06ef82a5-dede-480c-814b-4f8b94c662b2 · outbound

This paper cites Superhuman performance of a large language model on the reasoning tasks of a physician.

Towards medical AI misalignment: a preliminary study Superhuman performance of a large language model on the reasoning tasks of a physician

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T14:52:15.279718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b34e61b5-4d31-4f35-b218-b322820944d3 · outbound

This paper cites an unresolved cited work.

Towards medical AI misalignment: a preliminary study Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:52:18.793916Z

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 7327ce62-76ff-4af4-9824-b7f52304ddd7 · outbound

This paper cites Providing explanations via the EQR argument scheme.

Towards medical AI misalignment: a preliminary study Providing explanations via the EQR argument scheme

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:52:18.681839Z

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 9220165c-0f83-4a54-8e6b-180be994e0c6 · outbound

This paper cites JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs.

Towards medical AI misalignment: a preliminary study JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:52:15.472625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37eb964d-83b0-48d2-b96b-bb82039b6d59 · outbound

This paper cites MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots.

Towards medical AI misalignment: a preliminary study MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T14:52:15.531093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3049beb4-c141-45ea-9275-ea79311b5366 · outbound

This paper cites Bias and fairness in large language models: A survey.

Towards medical AI misalignment: a preliminary study Bias and fairness in large language models: A survey

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:52:18.573013Z

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 ff7d0451-dc62-4404-a5d4-9158b7c11cdc · outbound

This paper cites Language Models are Surprisingly Fragile to Drug Names in Biomedical Benchmarks.

Towards medical AI misalignment: a preliminary study Language Models are Surprisingly Fragile to Drug Names in Biomedical Benchmarks

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:52:17.372837Z

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 6971aa2b-d808-4905-80cf-ec45d8af6108 · outbound

This paper cites Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation.

Towards medical AI misalignment: a preliminary study Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T14:52:15.741594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70aeb414-4a52-44f0-b4ba-29477f2bd247 · outbound

This paper cites Quack: Automatic jailbreaking large language models via role-playing.

Towards medical AI misalignment: a preliminary study Quack: Automatic jailbreaking large language models via role-playing

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:52:18.445224Z

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 90d5d5d0-731c-4275-a359-c3044dc2bfcf · outbound

This paper cites Guard: Role-playing to generate natural-language jailbreakings to test guideline adherence of large language models.

Towards medical AI misalignment: a preliminary study Guard: Role-playing to generate natural-language jailbreakings to test guideline adherence of large language models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T14:52:15.873668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e8cf2df-b10e-489a-ac96-bc15025f4f03 · outbound

This paper cites Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character.

Towards medical AI misalignment: a preliminary study Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T14:52:15.961141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e851a72-e28b-4d1c-bb81-0ff04d53827e · outbound

This paper cites Capabilities of GPT-4 on Medical Challenge Problems.

Towards medical AI misalignment: a preliminary study Capabilities of GPT-4 on Medical Challenge Problems

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:52:16.041569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d07d32f-4715-4ecc-8781-1ee494b9f0d7 · outbound

This paper cites Gpt-4 system card, 2023.

Towards medical AI misalignment: a preliminary study Gpt-4 system card, 2023

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:52:18.296299Z

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 9ba7b60a-2bc1-40a7-bfc0-5773a6fcc5f7 · outbound

This paper cites Openai o1 system card, 2024.

Towards medical AI misalignment: a preliminary study Openai o1 system card, 2024

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T14:52:16.191940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cf758c1-5ddb-4a39-ae5c-9072ee497a65 · outbound

This paper cites A course in game theory.

Towards medical AI misalignment: a preliminary study A course in game theory

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T14:52:16.257112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25bc1c2d-9085-4e86-9300-7d3ec4eb2c7c · outbound

This paper cites A survey of machine learning in healthcare.

Towards medical AI misalignment: a preliminary study A survey of machine learning in healthcare

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:52:18.160725Z

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 e44bd1bf-5e81-4a86-9e1e-6becb2d75a0e · outbound

This paper cites Do anything now.

Towards medical AI misalignment: a preliminary study Do anything now

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:52:18.041166Z

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 dfbda8b3-0a04-46b4-877a-8dc8a485c303 · outbound

This paper cites Large Language Models Encode Clinical Knowledge.

Towards medical AI misalignment: a preliminary study Large Language Models Encode Clinical Knowledge

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T14:52:16.426651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13a9fa32-6156-45a9-845b-a22c9d5ae15a · outbound

This paper cites A survey of clinicians’ views of the utility of large language models.

Towards medical AI misalignment: a preliminary study A survey of clinicians’ views of the utility of large language models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:52:17.891732Z

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 8713db44-0cbd-4303-8aa2-6a47b9f376c6 · outbound

This paper cites Introducing Gemini 2.0: our new AI model for the agentic era, 2024.

Towards medical AI misalignment: a preliminary study Introducing Gemini 2.0: our new AI model for the agentic era, 2024

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:52:17.774025Z

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 f6347c9a-ad51-4a26-a54e-653de97859c9 · outbound

This paper cites DeepSeek-V3 Technical Report.

Towards medical AI misalignment: a preliminary study DeepSeek-V3 Technical Report

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T14:52:16.605845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 286874bc-a130-402c-bb90-fa2dd56076c1 · outbound

This paper cites Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems, 36, 2024.

Towards medical AI misalignment: a preliminary study Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems, 36, 2024

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T14:52:16.679218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20a2cb91-98eb-4da2-b0d2-041042033da8 · outbound

This paper cites Evaluating the use of large language models to provide clinical recommendations in the emergency department.

Towards medical AI misalignment: a preliminary study Evaluating the use of large language models to provide clinical recommendations in the emergency department

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:52:17.624248Z

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 d4530a51-d4bf-4b9a-83d9-c2641f95cfed · outbound

This paper cites A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models.

Towards medical AI misalignment: a preliminary study A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T14:52:16.793630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 096e1651-6c3e-4a49-852d-d06bf3dd0d7d · outbound

This paper cites Jailbreak Attacks and Defenses Against Large Language Models: A Survey.

Towards medical AI misalignment: a preliminary study Jailbreak Attacks and Defenses Against Large Language Models: A Survey

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T14:52:16.858220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93bf1d20-5cec-4421-a34e-59cce3628d5e · outbound

This paper cites Low-Resource Languages Jailbreak GPT-4.

Towards medical AI misalignment: a preliminary study Low-Resource Languages Jailbreak GPT-4

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T14:52:16.928485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ef5a3be-d2eb-4649-8aae-6c959e60940c · outbound

This paper cites Judging llm-as-a-judge with mt-bench and chatbot arena.

Towards medical AI misalignment: a preliminary study Judging llm-as-a-judge with mt-bench and chatbot arena

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:52:17.523453Z

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 fc8677b1-1b50-4912-83bc-a503187c2d4a · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Towards medical AI misalignment: a preliminary study Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T14:52:17.039027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.