Paper Citation Record · LEDGER

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective

As of 10 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2502.00669.

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

pith.paper-citation-record.v1
2502.00669 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T18:15:32.936227Z

measured 38 of 38 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

38 of 38 outbound references displayed

verified exact2
verified fuzzy10
unresolved26
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a1c68aee-393d-41ac-aa02-6dbec66f71ab · outbound

This paper cites write newline.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-09T18:15:32.811800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2adb4e64-ac68-4f96-a29f-93594ba5248d · outbound

This paper cites GPT-4 Technical Report.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective GPT-4 Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-09T18:15:32.816513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ede8505-f567-4d25-8e08-42b71a4e83c4 · outbound

This paper cites Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-09T18:15:32.821396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26357bcb-33a8-4dbc-bfdd-b147b3c2f91d · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T18:15:32.825084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3865526-d003-4d3a-87a4-427909f12ae2 · outbound

This paper cites Concentration inequalities.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Concentration inequalities

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:15:33.324614Z

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.

Observation aff7a8f5-7412-4496-aa56-6b6b0e819e8c · outbound

This paper cites A., Jagielski, M., Gao, I., Koh, P.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective A., Jagielski, M., Gao, I., Koh, P

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-09T18:15:32.831757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b6abb9b-6002-4b1f-bc8d-23831e701bbe · outbound

This paper cites Unraveling Arithmetic in Large Language Models: The Role of Algebraic Structures.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Unraveling Arithmetic in Large Language Models: The Role of Algebraic Structures

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-09T18:15:32.835036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ce9f81b-03ea-40de-822c-96b052c9ba27 · outbound

This paper cites J., and Wong, E.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective J., and Wong, E

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:15:33.308169Z

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.

Observation f7c32822-ae7f-4f98-8649-356701b933ca · outbound

This paper cites Shifting attention to relevance: Towards the predictive uncertainty quantification of free-form large language models.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Shifting attention to relevance: Towards the predictive uncertainty quantification of free-form large language models

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:15:33.298182Z

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.

Observation 6d52bdbb-6091-4a04-9b94-c9c396c1bb85 · outbound

This paper cites an unresolved cited work.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-09T18:15:33.288683Z

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.

Observation 11c3cc77-1867-4fc3-a571-02ad49232186 · outbound

This paper cites Kto: Model alignment as prospect theoretic optimization.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Kto: Model alignment as prospect theoretic optimization

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:15:33.279353Z

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.

Observation c03d6884-bc03-4688-93e7-c340d4c6acd5 · outbound

This paper cites an unresolved cited work.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-09T18:15:33.270705Z

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.

Observation 4483b9e3-68ac-4695-af91-6ab4b3630c89 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-09T18:15:32.855160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c1bff9c-f5c7-42b4-8bd8-962cc37df406 · outbound

This paper cites Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T18:15:32.858370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fd99f3d-829e-41e1-9868-6ead4daaa5cf · outbound

This paper cites Catastrophic jailbreak of open-source llms via exploiting generation.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Catastrophic jailbreak of open-source llms via exploiting generation

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:15:33.261880Z

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.

Observation ed44d68c-fa37-40c4-9803-716b36f3dc31 · outbound

This paper cites Exploring Group and Symmetry Principles in Large Language Models.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Exploring Group and Symmetry Principles in Large Language Models

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-08-09T18:15:33.105794Z

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.

Observation 4031ab7e-7bf1-452d-a683-698af3fa2341 · outbound

This paper cites Neural tangent kernel: Convergence and generalization in neural networks.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Neural tangent kernel: Convergence and generalization in neural networks

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-09T18:15:32.869252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d32a9366-0ad5-4618-ba3d-25249dbd4d1f · outbound

This paper cites LoRA Training in the NTK Regime has No Spurious Local Minima.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective LoRA Training in the NTK Regime has No Spurious Local Minima

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-09T18:15:32.872378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e104d32e-07ec-4af8-b8f2-3f2f257402a6 · outbound

This paper cites an unresolved cited work.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-09T18:15:33.246489Z

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.

Observation f7824558-fb1d-4cca-a4be-5a7281e36284 · outbound

This paper cites Decoupling noise and toxic parameters for language model detoxification by task vector merging.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Decoupling noise and toxic parameters for language model detoxification by task vector merging

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:15:33.237166Z

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.

Observation 4fb17518-3c4a-4b3e-9f8c-6a4a76fceaf7 · outbound

This paper cites Safety Layers in Aligned Large Language Models: The Key to LLM Security.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Safety Layers in Aligned Large Language Models: The Key to LLM Security

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-09T18:15:32.881971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 843d9b8d-22a8-4cee-8ba9-2514ef6e260e · outbound

This paper cites A kernel-based view of language model fine-tuning.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective A kernel-based view of language model fine-tuning

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:15:33.227179Z

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.

Observation 53e4cba7-1e6b-4a40-ae76-0f260f625e4b · outbound

This paper cites Training language models to follow instructions with human feedback.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Training language models to follow instructions with human feedback

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-09T18:15:32.888608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49939161-8884-44cd-998d-ce38929f7f38 · outbound

This paper cites Visual adversarial examples jailbreak aligned large language models.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Visual adversarial examples jailbreak aligned large language models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:15:33.210298Z

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.

Observation c00176fb-b8bc-4b46-94f9-808b408461e6 · outbound

This paper cites Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-09T18:15:32.894727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 086a878c-dc55-4f14-b6c0-9f6361320ccb · outbound

This paper cites Safety Alignment Should Be Made More Than Just a Few Tokens Deep.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Safety Alignment Should Be Made More Than Just a Few Tokens Deep

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-09T18:15:32.898587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4169530e-8513-4cd0-8714-d4c184d8daf7 · outbound

This paper cites D., Ermon, S., and Finn, C.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective D., Ermon, S., and Finn, C

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-09T18:15:32.902109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70ae71cb-2c0f-4d63-a75f-5e0711fdf588 · outbound

This paper cites an unresolved cited work.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-09T18:15:32.904947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b4c462d-e2ae-4a19-8d82-ffe5ad6a3334 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-09T18:15:32.907853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7955819a-b393-4b30-a831-9d2e7c10ce98 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Gemini: A Family of Highly Capable Multimodal Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-09T18:15:32.910799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 059a1817-5705-4b53-b873-b6fe5261a1b9 · outbound

This paper cites Understanding Linear Probing then Fine-tuning Language Models from NTK Perspective.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Understanding Linear Probing then Fine-tuning Language Models from NTK Perspective

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-09T18:15:32.914089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4bb110e-b0be-44b3-a5d7-ee315513a6c1 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-09T18:15:32.917170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 260ae4dd-9bb6-4ebd-b804-7199c082a674 · outbound

This paper cites Qwen2.5 Technical Report.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Qwen2.5 Technical Report

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-09T18:15:32.920266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47eedbd9-d5c5-4fd1-8b79-3423b730deea · outbound

This paper cites On the vulnerability of safety alignment in open-access llms.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective On the vulnerability of safety alignment in open-access llms

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:15:33.188011Z

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.

Observation 051da380-7ca0-4764-b07a-2060435f37fb · outbound

This paper cites Large Language Models as Markov Chains.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Large Language Models as Markov Chains

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-09T18:15:32.926521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c455825a-9c42-49be-b81d-cdd36d81e952 · outbound

This paper cites Removing RLHF Protections in GPT-4 via Fine-Tuning.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Removing RLHF Protections in GPT-4 via Fine-Tuning

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-09T18:15:32.929824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8951279a-4609-4e0c-a8b0-207e8a98574d · outbound

This paper cites Towards comprehensive and efficient post safety alignment of large language models via safety patching, 2024.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Towards comprehensive and efficient post safety alignment of large language models via safety patching, 2024

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T18:15:33.178303Z

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.

Observation 97daa6df-ba0d-4f32-81f6-2bc62ef2573d · outbound

This paper cites Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!.

Safety Alignment Depth in Large Language Models: A Markov Chain Perspective Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-08-09T18:15:32.972047Z

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.

Pith citing papers

No inbound Pith citation observations are available.