Pith. sign in

Paper Citation Record · LEDGER

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing

As of 6 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 0 inbound Pith citation observations for arXiv:2605.25893.

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

pith.paper-citation-record.v1
2605.25893 v1

Coverage vector

measured 55 of 55 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-29T22:03:25.762772Z

measured 55 of 55 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+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

55 of 55 outbound references displayed

  • verified exact15
  • verified fuzzy0
  • unresolved36
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c4b3d9e5-0e28-4adf-bc87-735cee28cea3 · outbound

This paper cites Attention is all you need,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Attention is all you need,

Reference 1

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:95d8c5af2fd5cc9622c525960a4f3daf23c7842ba2ae7236f01157955314d293

Observation fa59df0a-fce2-4d02-8490-194f7d5048eb · outbound

This paper cites GPT-4 Technical Report.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing GPT-4 Technical Report

Reference 2

Resolution
verified exact
local_arxiv, observed 2026-06-29T22:03:59.810996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:5f7c819b292d838813cd3d4a8d01f0f14950c657f579f59878c99823ab9de964

Observation c4a92f76-c2c2-4d38-a57f-d9d2dadb83af · outbound

This paper cites The Llama 3 Herd of Models.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing The Llama 3 Herd of Models

Reference 3

Resolution
verified exact
local_arxiv, observed 2026-06-29T22:03:59.802963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:2ac7063fbd85a7a661fd01d61ecf6b329edc525fb8e02d4234b8822f7e0e269d

Observation c707e47c-82d0-4298-a708-5183e42157b3 · outbound

This paper cites Qwen3 Technical Report.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Qwen3 Technical Report

Reference 4

Resolution
verified exact
local_arxiv, observed 2026-06-29T22:03:59.816175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:aff3f47845752e3ff8a1afec21adb6dc21b6e865968e16fe1ca9b9322244db21

Observation f96d7e2f-922f-46a7-b1fa-c9650eaa7ea1 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Evaluating Large Language Models Trained on Code

Reference 5

Resolution
verified exact
local_arxiv, observed 2026-06-29T22:03:59.823612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:ac68e2cb08bf64bbb6a9c6cbde2439439b8ff5be971fc323eea05bbbb347568a

Observation cbe29160-a631-4b77-9f69-e0cf1cebab9d · outbound

This paper cites Competition-level code generation with alphacode,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Competition-level code generation with alphacode,

Reference 6

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:8f30117efa57df07186dd69b0188067f13836260634e6d27c6ee4ec618399465

Observation 4f7f0d7e-7dee-423b-9ede-2931452e6faf · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Training Verifiers to Solve Math Word Problems

Reference 7

Resolution
verified exact
local_arxiv, observed 2026-06-29T22:03:59.805623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:49a3f8fc5eced08b45767afdd7bc8ba6d0af5b3e47547f6e370d7e8cd602ec74

Observation 79f8ccbe-f301-4ab8-8fa0-c9f0769d96cf · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Chain-of-thought prompting elicits reasoning in large language models,

Reference 8

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:fc01be697e2d6e03bdf53d592ca23ec293df14112b75ee6fc42d74db4a4dcfc7

Observation 1ed8758a-5ceb-488a-a8c7-2648bc9bfe7b · outbound

This paper cites Large language diffusion models,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Large language diffusion models,

Reference 9

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:b4dd4162ef4e3cddae4ad80496c3b2f88e28d288ee2319b205f97699e948b63e

Observation 1c7f4de7-6368-481f-94ac-5f058bfe8d24 · outbound

This paper cites LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models

Reference 10

Resolution
verified exact
local_arxiv, observed 2026-06-29T22:03:59.844223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:33fdf27308f3ea1a2ebcbf9adbbdf4d64050b5592a6ee541e5a57d4156504d42

Observation b3b7718d-8fd0-446f-9b08-73e71381b57f · outbound

This paper cites LLaDA2.0: Scaling Up Diffusion Language Models to 100B.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing LLaDA2.0: Scaling Up Diffusion Language Models to 100B

Reference 11

Resolution
verified exact
local_arxiv, observed 2026-06-29T22:03:59.826196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:7a54f933b9db165b79e1ca980c5a24ac54c4091668cc2deaedfa020d7c54a035

Observation 821f8113-a3dd-4d60-834d-2a4763758a3b · outbound

This paper cites Mercury: Ultra-Fast Language Models Based on Diffusion.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Mercury: Ultra-Fast Language Models Based on Diffusion

Reference 12

Resolution
verified exact
local_arxiv, observed 2026-06-29T22:03:59.830296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:0cc553825ef94eb9bcbde6a18d3c1bd7d5297697e93378188bee796135a2288d

Observation 2d5f2e4e-9e7f-4700-9113-38c519666781 · outbound

This paper cites Simple and effective masked diffusion language models,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Simple and effective masked diffusion language models,

Reference 13

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:e53e8fdbb429d523b6c7c9ea984ffa10b62ce638642946330fa3a4298a612bc6

Observation ff568cf6-bc59-424b-8858-6dd7a234c8e8 · outbound

This paper cites Simplified and generalized masked diffusion for discrete data,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Simplified and generalized masked diffusion for discrete data,

Reference 14

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:aec6393eda807ff7443e489fca019bdc55f9cb1e2688820ff3bedcef9e0fb12a

Observation 24942b34-87fd-4995-90d1-4a4b86de3759 · outbound

This paper cites Introducing mercury 2.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Introducing mercury 2

Reference 15

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:c40ebd46ea09ccec32b34d93b876c3270a47de8da50c997a5552712d4305702a

Observation d6a2459c-3db8-4b3c-be6b-4f2f854518c9 · outbound

This paper cites Disrupting the first reported ai-orchestrated cyber espionage campaign.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Disrupting the first reported ai-orchestrated cyber espionage campaign

Reference 16

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:5789e52755931c414b54f026253a88e92eee14b7d001d043c31e29521d58ffd7

Observation 6c85bb3b-d0af-4565-8e68-c1a74712dea2 · outbound

This paper cites A2d: Any-order, any-step safety alignment for diffusion language models,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing A2d: Any-order, any-step safety alignment for diffusion language models,

Reference 17

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:0c68677ff01ffcae095e10ca864588f9c8e140b06832478d0abba15be405fef1

Observation 222cb686-004f-4255-9af6-fb2257aaebf9 · outbound

This paper cites Diffuguard: How intrinsic safety is lost and found in diffusion large language models,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Diffuguard: How intrinsic safety is lost and found in diffusion large language models,

Reference 18

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:7347053a5c989554ef498251fb111bb3d8ec390ab5e4b335fef9238beea9966f

Observation 71917975-4373-4408-bb9d-e8abd4d48841 · outbound

This paper cites The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections

Reference 19

Resolution
verified exact
local_arxiv, observed 2026-06-29T22:03:59.821194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:404264e3eee1b4f49c012f0168020bd6b0b0e1b8ded509a54d27b1014fa9d003

Observation 69cff78a-73b8-4223-b6cf-70bc7446a4a1 · outbound

This paper cites Wildguard: Open one-stop moderation tools for safety risks, jailbreaks, and refusals of llms,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Wildguard: Open one-stop moderation tools for safety risks, jailbreaks, and refusals of llms,

Reference 20

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:bedd5e6676f0be0e8b4d9317a0a265ea7ca824c3fd6eea6edae5d01d5ab77889

Observation 4ab5d1d9-bdcb-4dab-8446-06510af96377 · outbound

This paper cites Detecting strategic deception with linear probes,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Detecting strategic deception with linear probes,

Reference 21

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:8239ea17b69f5b93065c2e1fa2634f82eaf9859563b688760ede010a250556c3

Observation a9db752b-ce72-4c53-b879-bebc98675a54 · outbound

This paper cites Simple probes can catch sleeper agents, 2024,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Simple probes can catch sleeper agents, 2024,

Reference 22

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:090808d321163267b628f04a6545abf9394d48750df8d35f3e7569874e7a88de

Observation 8dc83a9d-5b53-45ac-8b15-08bab13cd5f2 · outbound

This paper cites Detecting high-stakes interactions with activation probes,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Detecting high-stakes interactions with activation probes,

Reference 23

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:41769d09dd0de123c6c1ce818cd974c4abf16b14d69d9f17b2a5f393a556859d

Observation 9b4966e2-93d0-4136-8e40-47b26c6b95eb · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 24

Resolution
verified exact
local_arxiv, observed 2026-06-29T22:03:59.847396Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:2fa3dbc48ae027262a80ec7fb25a9e05d6432f0f8fcc8f89316c847a883e50e2

Observation d826f66f-91a9-43c1-bd93-c860745488c3 · outbound

This paper cites ShieldGemma 2: Robust and Tractable Image Content Moderation.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing ShieldGemma 2: Robust and Tractable Image Content Moderation

Reference 25

Resolution
metadata mismatch
arxiv_id, observed 2026-06-29T22:03:59.797888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:521d3df85afe8e4c5a7a0db38efd2518accb68284fd5774e1dc3a9083a050429

Observation dd9b4d09-eaa5-45b6-95be-c3ef727df14a · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Understanding intermediate layers using linear classifier probes

Reference 26

Resolution
verified exact
local_arxiv, observed 2026-06-29T22:03:59.800377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:35e93f9f6beb5ead0b67ba49cbcbecc5e5e58110efed087cf6659a4eb630b3db

Observation ff08a188-0467-4cd3-a182-3202abf7febf · outbound

This paper cites Locating and editing factual associations in gpt,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Locating and editing factual associations in gpt,

Reference 27

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:350b3336d8a7aa8d21a31ccfc1ec926567a4a2c192cff98381a1c0f85bb26fc6

Observation 87309dd3-47b8-4673-bbd3-43165e50579e · outbound

This paper cites Kramár János, Engels Joshua, Wang Zheng, Chughtai Bilal, Shah Rohin, Nanda Neel, Conmy Arthur.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Kramár János, Engels Joshua, Wang Zheng, Chughtai Bilal, Shah Rohin, Nanda Neel, Conmy Arthur

Reference 28

Resolution
metadata mismatch
arxiv_id, observed 2026-06-29T22:03:59.838636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:c31165ac5f5ef73cf3289a8d51e44c77fe17c391c97ae99f26d7c61ac7ca6eae

Observation f3c81325-0ca6-4187-ba7c-5b552e1b63ac · outbound

This paper cites Time is a feature: Exploiting temporal dynamics in diffusion language models,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Time is a feature: Exploiting temporal dynamics in diffusion language models,

Reference 29

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:578c031a9c049c017a24dd61c44352e8cd0d916c46ed3daed37076562a089672

Observation 8432481d-fb02-4336-aece-7e7c7ab1a684 · outbound

This paper cites Diffusion language model knows the answer before it decodes,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Diffusion language model knows the answer before it decodes,

Reference 30

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:89cafd9e32a210530942ed987c1e0d6c52f3360e6f03f719cd4e9692328c1f97

Observation 91385343-f9a8-4c3d-a60d-d8b62f196969 · outbound

This paper cites Structured denoising diffusion models in discrete state-spaces,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Structured denoising diffusion models in discrete state-spaces,

Reference 31

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:162e73b049168f4bfa56382ea3d9ed7c8bf579feef91bcb44206ad40bad76bc7

Observation 6a4e8309-db99-4235-a20a-930f0e4230dc · outbound

This paper cites Argmax flows and multinomial diffusion: Learning categorical distributions,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Argmax flows and multinomial diffusion: Learning categorical distributions,

Reference 32

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:7ee0a696f9da87ccdb3cb5586afbf7a81c1e638bbe5e99307bf44f953ed9c420

Observation 52baab10-04a7-4a49-989c-0da0f48be560 · outbound

This paper cites Scaling up masked diffusion models on text,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Scaling up masked diffusion models on text,

Reference 33

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:78b436445aebf38cef2494dc546ed3f311d3718e8c6be2db9ae68c74c96cf432

Observation 7b5f4e39-6078-4969-b22b-90fd4037ab51 · outbound

This paper cites Diffusion models: A comprehensive survey of methods and applications,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Diffusion models: A comprehensive survey of methods and applications,

Reference 34

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:06f0b81f77d0116bc710433dc63a3cbd7174fcacf1e76f0a0979beabbf9846b0

Observation d0b43e74-88da-42fb-91da-cdff7a517bef · outbound

This paper cites 2026 , journal =.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing 2026 , journal =

Reference 35

Resolution
metadata mismatch
arxiv_id, observed 2026-06-29T22:03:59.841599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:652dc44bd929c520fd4e21796838235c6f5bb128295843acd21d5612a2e5e0af

Observation e662a3ba-5b18-48e2-8f8e-ca6651208293 · outbound

This paper cites AutoDAN: Generating stealthy jailbreak prompts on aligned large language models,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing AutoDAN: Generating stealthy jailbreak prompts on aligned large language models,

Reference 36

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:3bf2a03e055b0f79117391bdf2b62b074cf0cb5ea38e55a3f35760b88285bfee

Observation c2c362c3-6536-4336-a6ff-d2a63b237c99 · outbound

This paper cites How johnny can persuade llms to jailbreak them: Rethinking persuasion to challenge ai safety by humanizing llms,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing How johnny can persuade llms to jailbreak them: Rethinking persuasion to challenge ai safety by humanizing llms,

Reference 37

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:f7c3018473d0d939c70494c30af1c803a3627c72c1e99ce953b38b48b15da3d0

Observation 01295594-4342-46e3-b788-a3c736d88664 · outbound

This paper cites The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer

Reference 38

Resolution
verified exact
local_arxiv, observed 2026-06-29T22:03:59.818695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:0772384213389f2b6c9ffcd4493d976e655955f4e548a145a32be08c7be77185

Observation ff7ee886-a81f-4f2b-8cc0-e25167970f91 · outbound

This paper cites Using gpt-4 for content moderation,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Using gpt-4 for content moderation,

Reference 39

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:1bf3004dcd423a027c9a73e4419301b1d5f5c83cf56285d51fb894f767ac3fc7

Observation 53134286-079f-4312-8f2b-caeac44588f7 · outbound

This paper cites The linear representation hypothesis and the geometry of large language models,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing The linear representation hypothesis and the geometry of large language models,

Reference 40

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:31cd0ab728dd002d1c9e7e33034a53140a060291eda8bfc456bf2bf163ddfdc9

Observation d0a543bb-38c5-4049-9436-d665510bcefb · outbound

This paper cites Simple factuality probes detect hallucinations in long-form natural language generation,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Simple factuality probes detect hallucinations in long-form natural language generation,

Reference 41

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:d0f6e479aa44dd1786396861936a8eb85123abd5cfc6bc16ce606573e22d7353

Observation 147867d9-1fa8-4357-a395-22c58a294138 · outbound

This paper cites Toxicity detection for free,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Toxicity detection for free,

Reference 42

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:40e2e44094110ef5b105ad0729d6617bd620ffcb2a72db465a1372cbb8972f9f

Observation 6f269195-d5ac-4f2b-a1db-ea7683ad8b3b · outbound

This paper cites Branchynet: Fast inference via early exiting from deep neural networks,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Branchynet: Fast inference via early exiting from deep neural networks,

Reference 43

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:06a494e19892a872ab5dbec902d3bfb21ae9781059ce6c065d0bf1832a95dd52

Observation dcb21aa1-ce06-4d5c-8104-ffd45b45f3cb · outbound

This paper cites Designing and interpreting probes with control tasks,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Designing and interpreting probes with control tasks,

Reference 44

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:fa7602e1a72fb5939233dcde767772c3018218805ab5738e33730d3e5520326a

Observation 75c3eedf-7cdf-4fe2-9428-e5b246a7b6b9 · outbound

This paper cites Pareto probing: Trading off accuracy for complexity,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Pareto probing: Trading off accuracy for complexity,

Reference 45

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:1e32e23a7078f39edfc539520a0505108c6e8eddc232b56d10bbfcbfbbb2dce2

Observation 4e268064-2f0b-49f3-ad31-3b629270e8c6 · outbound

This paper cites Cost-effective constitutional classifiers via representation re-use.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Cost-effective constitutional classifiers via representation re-use

Reference 46

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:88f8d7e9248ff998b913786d2ed9079dc2bfe82d0cad77f7b456245431c67d6e

Observation 5fbcac87-e5e6-4517-bd24-c156e0d37c6d · outbound

This paper cites Beyond linear probes: Dynamic safety monitoring for language models,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Beyond linear probes: Dynamic safety monitoring for language models,

Reference 47

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:d6f5e984238f4c573ffb4bc909721697690ea50d6c364b1c582c8857157df77b

Observation 02c7583a-fd77-448a-bcc5-33700811b2ec · outbound

This paper cites Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks //.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks //

Reference 48

Resolution
verified exact
arxiv_id, observed 2026-06-29T22:03:59.833541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:5bf639a91253e5ebbc02c4982908a66852958f6a7d2eef2e2c0acf542e32699d

Observation acac264f-c9f0-4cd9-8908-8c2cd7942cee · outbound

This paper cites Probing classifiers: Promises, shortcomings, and advances,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Probing classifiers: Promises, shortcomings, and advances,

Reference 49

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:05056911f5d8a14b9ec55ad63278d69e8a1147b9f03baa1e54680d8715466c60

Observation 4a2140c6-4deb-4d75-a541-0a7e1e6edfef · outbound

This paper cites A non-linear structural probe,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing A non-linear structural probe,

Reference 50

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:3c86c935b624533684921ad04f3e2a778c491df687725e8f2d81201b2d1a2eda

Observation a6f90c1e-bccc-4b18-80ae-5c220080e0b2 · outbound

This paper cites Toxicchat: Unveiling hidden challenges of toxicity detection in real-world user-ai conversation,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Toxicchat: Unveiling hidden challenges of toxicity detection in real-world user-ai conversation,

Reference 51

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:265bfd2f552aba381b1358f78768eb8454927805b6144ae962b63b5d8cfc3f0a

Observation 05c10576-7de2-48e1-9a74-96b54911bc59 · outbound

This paper cites A Holistic Approach to Undesired Content Detection in the Real World.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing A Holistic Approach to Undesired Content Detection in the Real World

Reference 52

Resolution
verified exact
arxiv_id, observed 2026-06-29T22:03:59.808267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:491ebc731aafeb5dcaae894792e917e3326c8a2f41ce3358a827e68cbfb09b5f

Observation fa49c98d-3073-470a-97c7-b71bad5db96f · outbound

This paper cites Truth as a trajectory: What internal representations reveal about large language model reasoning,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Truth as a trajectory: What internal representations reveal about large language model reasoning,

Reference 53

Resolution
unresolved
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:de5b32ae254fcd07ebd7b523f4bc8342720741acc70fc98d5460c6bfc6d61a89

Observation 7ff3f069-5375-4ca0-bcba-5183e8158244 · outbound

This paper cites LLaDA2.1 : Speeding up text diffusion via token editing.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing LLaDA2.1 : Speeding up text diffusion via token editing

Reference 54

Resolution
verified exact
arxiv_id, observed 2026-06-29T22:03:59.813624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:24bc4f235653cfbfe1b33b10b2a6f9d6e6e326e7b9de7c76aff9b3d6da0d5923

Observation f11d8fdf-7794-410d-868b-e2ca7e38fe9c · outbound

This paper cites Obfuscated activations bypass LLM latent-space defenses,.

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing Obfuscated activations bypass LLM latent-space defenses,

Reference 55

Resolution
malformed identifier
no resolver link, observed 2026-06-29T22:03:25.762772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-29T22:03:25.762772Z digest=sha256:11251c5b62b385e6d8aeaa1dc9e1ab003c7aa61643c6588892ab20f2e4046df0

Pith citing papers

No inbound Pith citation observations are available.