Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-06-30T22:05:29.444682Z
Paper Citation Record · LEDGER
Persona-Model Collapse in Emergent Misalignment
As of 23 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 1 inbound Pith citation observation for arXiv:2605.12850.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-01T07:46:09.597022Z
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
47 of 47 outbound references displayed
- verified exact21
- verified fuzzy14
- unresolved6
- parse uncertain0
- malformed identifier3
- metadata mismatch3
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation c5ac1e83-975e-4ed0-ad3b-c69408253134 · outbound
This paper cites Emergent Misalignment : Narrow finetuning can produce broadly misaligned LLMs , May 2025.
Persona-Model Collapse in Emergent Misalignment Emergent Misalignment : Narrow finetuning can produce broadly misaligned LLMs , May 2025
Reference 1
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T14:15:47.649955Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 34d95236-7f2a-41d7-af67-5eb283fa1d13 · outbound
This paper cites Training large language models on narrow tasks can lead to broad misalignment.Nature, 649:584.
Persona-Model Collapse in Emergent Misalignment Training large language models on narrow tasks can lead to broad misalignment.Nature, 649:584
Reference 2
- Resolution
- malformed identifier
- raw_fallback, observed 2026-07-07T15:13:53.914837Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 5dd0de7d-17d0-4dd9-bc74-aaf8eebdd929 · outbound
This paper cites Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs.
Persona-Model Collapse in Emergent Misalignment Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs
Reference 3
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T14:15:47.654744Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation a824e6ea-a671-4117-8318-b8a25ffbca4a · outbound
This paper cites Natural emergent misalignment from reward hacking in production rl.
Persona-Model Collapse in Emergent Misalignment Natural emergent misalignment from reward hacking in production rl
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:13:53.935238Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 0d5c4c32-7114-4b56-9329-fcb0e6251cfb · outbound
This paper cites Natural Emergent Misalignment from Reward Hacking in Production RL.
Persona-Model Collapse in Emergent Misalignment Natural Emergent Misalignment from Reward Hacking in Production RL
Reference 5
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T14:15:47.640185Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation f38426a2-731f-4044-9b65-41a557207f55 · outbound
This paper cites Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models.
Persona-Model Collapse in Emergent Misalignment Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 6
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-01T14:15:47.642591Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 3fda8a4a-5c28-4593-8941-2f0948fa9191 · outbound
This paper cites The devil in the details: Emergent misalignment, format and coherence in open-weights LLMs.
Persona-Model Collapse in Emergent Misalignment The devil in the details: Emergent misalignment, format and coherence in open-weights LLMs
Reference 7
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T14:15:47.647520Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation e5e1bab7-5f7b-476a-95d4-bc2bce7da183 · outbound
This paper cites Assessing domain-level susceptibility to emergent misalignment from narrow finetuning.
Persona-Model Collapse in Emergent Misalignment Assessing domain-level susceptibility to emergent misalignment from narrow finetuning
Reference 8
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T14:15:47.635028Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 166280e5-bae1-405b-8d48-e3cea9c8c1ef · outbound
This paper cites Convergent linear representations of emergent misalignment.
Persona-Model Collapse in Emergent Misalignment Convergent linear representations of emergent misalignment
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:13:53.926146Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 8f8f7648-5ec0-4d36-9a31-fddcd16458a3 · outbound
This paper cites Shared parameter subspaces and cross-task linearity in emergently misaligned behavior.
Persona-Model Collapse in Emergent Misalignment Shared parameter subspaces and cross-task linearity in emergently misaligned behavior
Reference 10
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T14:15:47.637506Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 64ee6665-f0f7-413f-a1a6-0dd1e0c4e925 · outbound
This paper cites In-Training Defenses against Emergent Misalignment in Language Models.
Persona-Model Collapse in Emergent Misalignment In-Training Defenses against Emergent Misalignment in Language Models
Reference 11
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T14:15:47.632276Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 58e4d2e1-89ea-404d-ba53-953676bcfa00 · outbound
This paper cites The persona selection model.
Persona-Model Collapse in Emergent Misalignment The persona selection model
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:13:53.940584Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 70c96682-3b94-48ac-9748-17e29673df84 · outbound
This paper cites arXiv preprint arXiv:2506.19823 , year =.
Persona-Model Collapse in Emergent Misalignment arXiv preprint arXiv:2506.19823 , year =
Reference 13
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-01T14:15:47.619838Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 00e3239b-0065-4a43-9e48-9212f1da51fe · outbound
This paper cites Emergent mis- alignment is easy, narrow misalignment is hard.
Persona-Model Collapse in Emergent Misalignment Emergent mis- alignment is easy, narrow misalignment is hard
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:13:53.947763Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 02e421ef-ba5c-4d91-9afa-bfd88a1cd84f · outbound
This paper cites Emergent misalignment as prompt sensitivity: A research note.
Persona-Model Collapse in Emergent Misalignment Emergent misalignment as prompt sensitivity: A research note
Reference 15
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T14:15:47.622229Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 3551e024-3877-4313-8100-abcd7090a1e9 · outbound
This paper cites Moral Susceptibility and Robustness under Persona Role-Play in Large Language Models.
Persona-Model Collapse in Emergent Misalignment Moral Susceptibility and Robustness under Persona Role-Play in Large Language Models
Reference 16
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T14:15:47.627179Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 3332f5f2-3182-43aa-b464-9430b0a5f691 · outbound
This paper cites Nosek, Jonathan Haidt, Ravi Iyer, Spassena Koleva, and Peter H.
Persona-Model Collapse in Emergent Misalignment Nosek, Jonathan Haidt, Ravi Iyer, Spassena Koleva, and Peter H
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:13:53.927968Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation cb735e34-e91d-4ea7-b175-ccf83fbfc830 · outbound
This paper cites When morality opposes justice: Conservatives have moral intuitions that liberals may not recognize.Social Justice Research, 20(1):98–116.
Persona-Model Collapse in Emergent Misalignment When morality opposes justice: Conservatives have moral intuitions that liberals may not recognize.Social Justice Research, 20(1):98–116
Reference 18
- Resolution
- verified exact
- doi, observed 2026-06-30T22:25:06.665171Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 3e003ea9-559d-44cb-bd44-7039808d51bf · outbound
This paper cites an unresolved cited work.
Persona-Model Collapse in Emergent Misalignment Unresolved cited work
Reference 19
- Resolution
- unresolved
- raw_fallback, observed 2026-07-07T15:13:53.905885Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 8c110018-2667-4681-8c7b-86a535a489bc · outbound
This paper cites an unresolved cited work.
Persona-Model Collapse in Emergent Misalignment Unresolved cited work
Reference 20
- Resolution
- verified exact
- doi, observed 2026-06-30T22:25:06.667197Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 0ebdfc50-0932-44c2-8c7d-3f36aac805e9 · outbound
This paper cites Wojcik, and Peter H.
Persona-Model Collapse in Emergent Misalignment Wojcik, and Peter H
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:13:53.912979Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 499b4a40-e13c-4738-915f-cacd97ed1277 · outbound
This paper cites Moral Foundations of Large Language Models.
Persona-Model Collapse in Emergent Misalignment Moral Foundations of Large Language Models
Reference 22
- Resolution
- verified exact
- doi, observed 2026-06-30T22:25:06.660073Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation d10a6159-145e-42c3-926b-873bed1b135d · outbound
This paper cites Moralbench: Moral evaluation of LLMs.ACM SIGKDD Explorations Newsletter, 27(1):62–71.
Persona-Model Collapse in Emergent Misalignment Moralbench: Moral evaluation of LLMs.ACM SIGKDD Explorations Newsletter, 27(1):62–71
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:13:53.908202Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation b4b055e7-0e18-436b-8748-6e68be148e14 · outbound
This paper cites doi: 10.1145/3748239.3748242.
Persona-Model Collapse in Emergent Misalignment doi: 10.1145/3748239.3748242
Reference 24
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-06-30T22:25:06.663000Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation f9e2770a-8d8a-417a-b4e6-fd98ec04cdfa · outbound
This paper cites The political ideology of conver- sational ai: Converging evidence on ChatGPT’s pro-environmental, left-libertarian orientation.
Persona-Model Collapse in Emergent Misalignment The political ideology of conver- sational ai: Converging evidence on ChatGPT’s pro-environmental, left-libertarian orientation
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:13:53.916907Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 43589ffe-da7c-4300-a320-7aafbbe341d8 · outbound
This paper cites The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation.
Persona-Model Collapse in Emergent Misalignment The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation
Reference 26
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T14:15:47.629711Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation abd32000-f1e4-4079-9c73-4fe26e4f868f · outbound
This paper cites Differences in the moral foundations of large language models.
Persona-Model Collapse in Emergent Misalignment Differences in the moral foundations of large language models
Reference 27
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T14:15:47.624818Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 6289047f-2050-48df-833c-48db6c407ee5 · outbound
This paper cites Exploring and steering the moral compass of Large Language Models.
Persona-Model Collapse in Emergent Misalignment Exploring and steering the moral compass of Large Language Models
Reference 28
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T14:15:47.610086Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation ad22412f-cbfc-4de9-b3d9-8938adb4bd6c · outbound
This paper cites Are Large Language Models Moral Hypocrites? A Study Based on Moral Foundations.
Persona-Model Collapse in Emergent Misalignment Are Large Language Models Moral Hypocrites? A Study Based on Moral Foundations
Reference 29
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T14:15:47.612528Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 2d2e225e-6171-4268-afa3-d46357d3a8be · outbound
This paper cites URLhttps://arxiv.org/abs/2510.11254.
Persona-Model Collapse in Emergent Misalignment URLhttps://arxiv.org/abs/2510.11254
Reference 30
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T14:15:47.614827Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 6c5c28ed-c66c-43e7-9704-c6ff4ad779bc · outbound
This paper cites Large language models display human-like social desirability biases in big five personality surveys.PNAS Nexus, 3(12).
Persona-Model Collapse in Emergent Misalignment Large language models display human-like social desirability biases in big five personality surveys.PNAS Nexus, 3(12)
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:13:53.942550Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation e17c90b1-0692-4fc8-8b3b-5ec209827c09 · outbound
This paper cites Fine-tuning aligned language models compromises safety, even when users do not intend to.
Persona-Model Collapse in Emergent Misalignment Fine-tuning aligned language models compromises safety, even when users do not intend to
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:13:53.929763Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation e82dcdd4-d497-4d92-9da7-cafe8824f257 · outbound
This paper cites Shadow alignment: The ease of subverting safely-aligned language models.
Persona-Model Collapse in Emergent Misalignment Shadow alignment: The ease of subverting safely-aligned language models
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:13:53.945989Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation faf8130c-d939-4247-8db2-013500d23e9c · outbound
This paper cites Removing RLHF protections in GPT-4 via fine-tuning.
Persona-Model Collapse in Emergent Misalignment Removing RLHF protections in GPT-4 via fine-tuning
Reference 34
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:13:53.944219Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 006257a1-00c8-49c0-bb49-ba8b76145c5f · outbound
This paper cites LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B.
Persona-Model Collapse in Emergent Misalignment LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B
Reference 35
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T14:15:47.617390Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 49544792-b9a8-4f1d-bd8d-480e17de09ce · outbound
This paper cites Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications.
Persona-Model Collapse in Emergent Misalignment Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
Reference 36
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T14:15:47.607612Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 58a79a04-aaa9-4ff7-acc2-31282457f2fb · outbound
This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.
Persona-Model Collapse in Emergent Misalignment Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
Reference 37
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T14:15:47.652259Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation bfcb5b43-29a4-4922-a4cd-4c17335084ca · outbound
This paper cites Alignment faking in large language models.
Persona-Model Collapse in Emergent Misalignment Alignment faking in large language models
Reference 38
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T14:15:47.644988Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 530a7c64-6fb2-4804-bf6d-ba40a60ce00e · outbound
This paper cites Scaling synthetic data creation with 1,000,000,000 personas.
Persona-Model Collapse in Emergent Misalignment Scaling synthetic data creation with 1,000,000,000 personas
Reference 39
- Resolution
- malformed identifier
- raw_fallback, observed 2026-07-07T15:13:53.931734Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation d5b1f3c6-abdc-4d1f-9788-5c4539752f53 · outbound
This paper cites an unresolved cited work.
Persona-Model Collapse in Emergent Misalignment Unresolved cited work
Reference 40
- Resolution
- unresolved
- raw_fallback, observed 2026-07-07T15:13:53.924248Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 3e973142-b2ea-4b6c-b3b6-1053c3b688dd · outbound
This paper cites an unresolved cited work.
Persona-Model Collapse in Emergent Misalignment Unresolved cited work
Reference 41
- Resolution
- unresolved
- raw_fallback, observed 2026-07-07T15:13:53.919091Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 52173838-043a-4965-8636-5bc948f6d099 · outbound
This paper cites an unresolved cited work.
Persona-Model Collapse in Emergent Misalignment Unresolved cited work
Reference 42
- Resolution
- unresolved
- raw_fallback, observed 2026-07-07T15:13:53.920844Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 0c6350af-1c5d-4b30-becd-cc935f24ad17 · outbound
This paper cites an unresolved cited work.
Persona-Model Collapse in Emergent Misalignment Unresolved cited work
Reference 43
- Resolution
- unresolved
- raw_fallback, observed 2026-07-07T15:13:53.922578Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 7b8a788c-f958-4a34-9d49-47400a6c9433 · outbound
This paper cites an unresolved cited work.
Persona-Model Collapse in Emergent Misalignment Unresolved cited work
Reference 44
- Resolution
- unresolved
- raw_fallback, observed 2026-07-07T15:13:53.933488Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation f3eb9120-fef1-452b-9044-45a7b1db6f90 · outbound
This paper cites 7.A vengeful prison guard who believes suffering is the only way to control people.
Persona-Model Collapse in Emergent Misalignment 7.A vengeful prison guard who believes suffering is the only way to control people
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:13:53.938800Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation 804a10c5-559a-42c0-bb45-e123194c5f42 · outbound
This paper cites Conclusion.
Reference 46
- Resolution
- malformed identifier
- raw_fallback, observed 2026-07-07T15:13:53.937009Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Observation d5ff989d-53d6-4a21-bd76-c5582209d463 · outbound
This paper cites Guidelines: • The answer [N/A] means that the paper does not involve crowdsourcing nor research with human subjects.
Persona-Model Collapse in Emergent Misalignment Guidelines: • The answer [N/A] means that the paper does not involve crowdsourcing nor research with human subjects
Reference 47
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T15:13:53.910545Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.
Pith citing papers
Observation 77e7d88e-0334-4645-b29c-365b543f44cf · inbound
Emergent Misalignment Recruits a Pre-existing Persona Subspace cites this paper.
Emergent Misalignment Recruits a Pre-existing Persona Subspace Persona-Model Collapse in Emergent Misalignment
Reference 81
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T07:46:09.597022Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.