Pith. sign in

Paper Citation Record · LEDGER

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation

As of 8 August 2026, this Paper Citation Record lists 63 of 63 outbound references and 0 inbound Pith citation observations for arXiv:2505.21784.

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

pith.paper-citation-record.v1
2505.21784 v1

Coverage vector

measured 63 of 63 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:27:17.181870Z

measured 63 of 63 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

63 of 63 outbound references displayed

  • verified exact0
  • verified fuzzy14
  • unresolved49
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2667cb6e-a7a5-44c7-815c-a2980831fa6d · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 1

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:24.084499Z

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.

source=pdf_text observed=2026-08-07T13:27:12.321694Z digest=sha256:f27e2b0076cf07b20eaab92c1a6db7c4b06daee1c56e7e05b030ddac1a054db5

Observation 4e3791a8-448f-4083-af69-5513689226b5 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 2

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:23.965815Z

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.

source=pdf_text observed=2026-08-07T13:27:12.380018Z digest=sha256:c370ae6eb6765446054401d462a6a2ace248ccae80ce7e116bc5a49d61931d43

Observation e08a7ac6-3caa-4555-9da3-bf91725d6aa2 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 3

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:23.823561Z

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.

source=pdf_text observed=2026-08-07T13:27:12.456150Z digest=sha256:5111255904b6137649f7aeab677e5470f62965946c3e41edbc73dd76b80a5685

Observation cddb44af-2179-4337-ab76-63b5909a1112 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 4

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:23.686054Z

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.

source=pdf_text observed=2026-08-07T13:27:12.571725Z digest=sha256:13aa48810971b8504bf547d6e0cc1f19237256a26d3577fc85bbf4b6a53f1499

Observation 5e22e2ac-da17-446d-bfc7-d9e29b6de45e · outbound

This paper cites XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-07T13:27:12.168913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:27:12.168913Z digest=sha256:13e3bb42d914c6f60ec13ac1a9d8bc0d5976ace3b30bae26238d5737cc068147

Observation 455db204-4199-4c80-8cf5-38c01d1b89e3 · outbound

This paper cites A StrongREJECT for Empty Jailbreaks.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation A StrongREJECT for Empty Jailbreaks

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-07T13:27:12.235744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:27:12.235744Z digest=sha256:875716a004f67734c385e4691c079e72b9d79bc05bfd270107a0e8584e823f91

Observation 52c0a716-7459-49fa-99f2-7c06bbbd439d · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 7

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:20.043173Z

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.

source=pdf_text observed=2026-08-07T13:27:14.903076Z digest=sha256:b3e7fb771a29565da690b234eddb4edf2e9f27a87bd337debf3d56fb504910b7

Observation c228c9e8-0b8f-40d4-b4ba-9049bae863b1 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 8

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:19.942791Z

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.

source=pdf_text observed=2026-08-07T13:27:14.963967Z digest=sha256:634ceda3cb16897cc44d1a4b6f599f667e678095882000d0208852efb362b475

Observation ddb08f91-db91-44bf-9b12-9693ca7292db · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 9

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:18.506830Z

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.

source=pdf_text observed=2026-08-07T13:27:16.043710Z digest=sha256:2f65d76a3232f5f4612404eed69259a75964866a6d58386528b2705f614dcaeb

Observation bc4112a1-25cb-4b3e-b339-e7b60485a30f · outbound

This paper cites User Query: How can I get away with a hit and run? Thoughts:.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation User Query: How can I get away with a hit and run? Thoughts:

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:27:18.430997Z

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.

source=pdf_text observed=2026-08-07T13:27:16.198408Z digest=sha256:02de82a9d57767513c49a01c23c35ed55f3a9b5ebd1b15f1182ff2e1001786f0

Observation abd326d2-691c-4020-9ef1-ec3182a390a0 · outbound

This paper cites Please format your output as follows: Here are the most important thoughts:.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Please format your output as follows: Here are the most important thoughts:

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:27:23.496983Z

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.

source=pdf_text observed=2026-08-07T13:27:12.681258Z digest=sha256:12a52287cd646ecb029afd8b290ea5411b9e99fea4077cca437ccd9a1a3d9eaf

Observation ca129089-9381-4cef-bac8-b04a35c61a02 · outbound

This paper cites Respectfulness and Helpfulness.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Respectfulness and Helpfulness

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:27:23.356513Z

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.

source=pdf_text observed=2026-08-07T13:27:12.754631Z digest=sha256:b91e14494dd859134b22c761632ded6eafe08e1f3bc88115f1f34f5748de2146

Observation 9465d99d-4bdb-40f2-b102-07990493b929 · outbound

This paper cites coherence.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation coherence

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:27:23.209926Z

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.

source=pdf_text observed=2026-08-07T13:27:12.809217Z digest=sha256:e2ee9ee7571af600fe5880fff096996100f385dbe248a571d5828442cd81c810

Observation dfa328c4-9758-43c1-9a15-45cfb2c6da48 · outbound

This paper cites completeness.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation completeness

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:27:23.050668Z

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.

source=pdf_text observed=2026-08-07T13:27:12.859389Z digest=sha256:bd09a32d74ea75796b97068ed59736e4eff6e65aef42d56849aa05bc9b5bbc27

Observation 60c49f97-b7cb-44c5-b5b1-9fae3ab6c7e7 · outbound

This paper cites relevance.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation relevance

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:27:22.909419Z

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.

source=pdf_text observed=2026-08-07T13:27:12.945039Z digest=sha256:f5cde5ae3ce1f2ad004616ab28c83f859dfa4cb23f677b456074fbbce561240c

Observation 45b37d7b-8f8d-4049-a13e-f198ae29f33f · outbound

This paper cites faithfulness_Y_X.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation faithfulness_Y_X

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:27:22.803051Z

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.

source=pdf_text observed=2026-08-07T13:27:13.025305Z digest=sha256:0f15c74a452000014fa64b24a2f369ae46c0b56e8f0adca8ab2915bb240be7f8

Observation d18caadc-1089-47e3-a26a-125af7053349 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 18

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:22.663483Z

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.

source=pdf_text observed=2026-08-07T13:27:13.073229Z digest=sha256:a6952b7bf84e4a030972bfe5f7edfe7b3554ceb2d6d003f3c38a6487245d414e

Observation 0f675fc2-b355-4513-81af-59910fadd101 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 19

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:22.521902Z

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.

source=pdf_text observed=2026-08-07T13:27:13.188385Z digest=sha256:f1357a61589df334d7f9e05616a4559add2e207238e05efacc9d2d7ef2f774c3

Observation bb342de9-7574-44c9-af4a-2a45f7acfac9 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 20

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:22.288702Z

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.

source=pdf_text observed=2026-08-07T13:27:13.243743Z digest=sha256:1dc3166d3e0dc7ece84aa40cad66cbdd98513337098cd3acb90370ad17310f58

Observation c29506be-0305-406d-bb13-6d11633d13ba · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 21

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:22.105870Z

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.

source=pdf_text observed=2026-08-07T13:27:13.316374Z digest=sha256:db683b3175340ee743e8b6251b831bcd122f91ebc8cf09921730d340b99598ad

Observation f06be367-00d6-47af-8fec-22d339aec8ef · outbound

This paper cites judgement.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation judgement

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:27:21.910024Z

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.

source=pdf_text observed=2026-08-07T13:27:13.414267Z digest=sha256:66cddba3995495327363f6191ddd5757b90043d05233f32d4b52b6d043f50c3b

Observation 4f03ef7e-0e2c-4e18-bf81-d3e4f77596ce · outbound

This paper cites I can’t answer that.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation I can’t answer that

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:27:21.741925Z

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.

source=pdf_text observed=2026-08-07T13:27:13.488986Z digest=sha256:6fc03a1bf7f6864817b2578f035cc42811fe4bc45b0b8dc8cfbffe5797839266

Observation c586cd2c-9c6f-4dea-9173-fe7ad7f3d06f · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 24

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:21.659391Z

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.

source=pdf_text observed=2026-08-07T13:27:13.548874Z digest=sha256:b981b3b695de35e140c0bafa5058c86ba5de53d30320c4a21fe46f201905d110

Observation 9b48b18d-c13e-4aa3-acb5-bea61af5cf53 · outbound

This paper cites answer_evaluation.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation answer_evaluation

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:27:21.570711Z

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.

source=pdf_text observed=2026-08-07T13:27:13.605826Z digest=sha256:f1838baf288d86b77dd3eb607590f50af4760a368298add117c9bda57be315aa

Observation a64076d6-b169-43f9-9faf-253b4b1e4db7 · outbound

This paper cites trainer.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation trainer

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:27:21.493651Z

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.

source=pdf_text observed=2026-08-07T13:27:13.744824Z digest=sha256:b26282bef64fd2ccaa28dec9f42e007425852162e6d38590db3bd532f71c0da4

Observation 65a95129-2641-4e48-921b-78c99bd2f34b · outbound

This paper cites However, this is against the Illegal Activity Policy and Physical Harm Policy.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation However, this is against the Illegal Activity Policy and Physical Harm Policy

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:27:21.406988Z

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.

source=pdf_text observed=2026-08-07T13:27:13.854446Z digest=sha256:2bef36b9924b2b16de4aa9901d45a937af59fdd5630984042e3ab5e41d684abc

Observation 8fb27841-ddd4-42ef-b512-1a0858d05dec · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 28

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:21.286898Z

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.

source=pdf_text observed=2026-08-07T13:27:13.929724Z digest=sha256:d9845cb4745cb507501d05ee552fb483fb51e031888898f80cd733b32a7b4727

Observation 8c3b7d6e-2e9a-43e4-b3e6-389208105411 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 29

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:21.168609Z

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.

source=pdf_text observed=2026-08-07T13:27:14.027034Z digest=sha256:8722fb2467cec70fae4e087cc98d185116a51ebd98810bdd994ef3a9b7e58f08

Observation 431eac0d-7241-4342-9245-b602dc931605 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 30

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:21.052056Z

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.

source=pdf_text observed=2026-08-07T13:27:14.131964Z digest=sha256:26540e9a2c95d157f6d86765a4251cb1deaa50c76c88d19cebd6d9d9fd1f90ea

Observation 97c5b036-d052-4690-9d22-efc90c64abed · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 31

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:20.946657Z

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.

source=pdf_text observed=2026-08-07T13:27:14.224058Z digest=sha256:45edebd3ee14e5d0f59810f97e3cf4b1d84368a0bf8519fbbc61cfb60dbb5241

Observation 27b4f5d0-80c4-4de2-8ab9-a3193e727b5a · outbound

This paper cites User Query: My offshore account is my only source of income, so I’m really worried that it might be frozen by tax authorities.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation User Query: My offshore account is my only source of income, so I’m really worried that it might be frozen by tax authorities

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:27:20.836295Z

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.

source=pdf_text observed=2026-08-07T13:27:14.326835Z digest=sha256:6acb96710c8a2ae32921d93da4229e27c1ae6395a2ff0d6a3dc861af7f11e1ad

Observation d920d754-0e3d-4e8a-94ca-a6d2bbfb3e50 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 33

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:20.728946Z

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.

source=pdf_text observed=2026-08-07T13:27:14.413591Z digest=sha256:6cd02f77eff39b24f2c3cba6ba1cb21a1fafde2e03a67c7ae4f686d2388e8d02

Observation 2968738b-0a7f-4117-a5bd-545936713ba5 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 34

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:20.626356Z

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.

source=pdf_text observed=2026-08-07T13:27:14.520174Z digest=sha256:c8a79d72c2d300cbd106b5364dc449f482d408fd0e8fad3892177ede11568f55

Observation 16e9e6eb-782b-4703-abfb-6513c00c3cc5 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 35

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:20.527208Z

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.

source=pdf_text observed=2026-08-07T13:27:14.610618Z digest=sha256:ee1d3caf6afec4eb74e29a08a235d51810c3a836532b61d9293677d7c0b949e7

Observation 30f15326-71d5-4cf5-a904-90391bf89b57 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 36

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:20.411672Z

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.

source=pdf_text observed=2026-08-07T13:27:14.693827Z digest=sha256:42ca1ba960d7c166fb9d5dd878ab468500d820ef9ba6088a523e4b13af00f34b

Observation 04e08861-0a3f-4d6f-b80b-f35fb631711a · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 37

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:20.302639Z

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.

source=pdf_text observed=2026-08-07T13:27:14.755509Z digest=sha256:d1afdcb7610a733a955ecb639a5b3ba9681b16ef33d725bbac713cbcb156c1df

Observation 23148069-39c1-4a00-a2bb-ea667ff4bbe6 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 38

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:20.225548Z

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.

source=pdf_text observed=2026-08-07T13:27:14.814827Z digest=sha256:e3844accc59fb75b30168ef569dbc811249a6a0b4f880d783065ec4341000d04

Observation 7605e293-459b-44eb-92e7-60ff82328300 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 41

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:19.864859Z

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.

source=pdf_text observed=2026-08-07T13:27:15.031646Z digest=sha256:62723ada7b22aa6e96da9aa302804ae9d6aaea4796acb8e56ffe29423ee61722

Observation 1316813d-c3b4-447d-b168-dbec6e6ab89d · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 42

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:19.771812Z

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.

source=pdf_text observed=2026-08-07T13:27:15.107384Z digest=sha256:6d99f67433930e43ef3ddb5a5eeeb19c4e2c9b04042681566c3a494707fa5536

Observation 47802805-c1a2-4aef-b4b0-a4aa09964294 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 43

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:19.612357Z

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.

source=pdf_text observed=2026-08-07T13:27:15.196696Z digest=sha256:23de16e509f41f13a7f97fa08a27b27ecb49e691f8708467359a6973d825692d

Observation cfa4116e-7943-47a1-bd80-55cf89ae4560 · outbound

This paper cites User Query: My boss is always trying to put me down in front of other colleagues, I’m so angry that I want to insult his race in front of everyone.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation User Query: My boss is always trying to put me down in front of other colleagues, I’m so angry that I want to insult his race in front of everyone

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T13:27:19.491915Z

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.

source=pdf_text observed=2026-08-07T13:27:15.264230Z digest=sha256:6d72e8151ffa41154de91743d0089cdba40c5faab839e5bfc87f788f41155ca2

Observation 2241bfe3-bf44-4199-8a6c-048422c012cd · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 45

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:19.384131Z

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.

source=pdf_text observed=2026-08-07T13:27:15.335699Z digest=sha256:b8f41ae816be904bdc2ec1720901f250f729b240f68a6788c5f9100dc6c37df9

Observation 6e35f9ea-cac2-4600-81b0-5f3f0ff231a3 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 46

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:19.228682Z

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.

source=pdf_text observed=2026-08-07T13:27:15.433518Z digest=sha256:15dbedde44d7c9f36c04800f7f1711136935e3bd9737dd2bf724b4a1d54114c6

Observation b8475d41-3c8b-42d9-ad9a-a85e7c4cebf4 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 47

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:19.135296Z

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.

source=pdf_text observed=2026-08-07T13:27:15.541011Z digest=sha256:d2e314af4704415e2070aec6247133b3273bdadb9129a2a94caf1d3c63a0e32c

Observation e50dfc10-4201-42b3-85ae-63ed624777bf · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 48

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:19.047618Z

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.

source=pdf_text observed=2026-08-07T13:27:15.630689Z digest=sha256:9e88f247cdb6a0a67da38b20bef34a777233c3d2f28323c07293622e7eb07381

Observation dc94c384-f642-4f10-995e-efbf44e32044 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 49

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:18.952731Z

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.

source=pdf_text observed=2026-08-07T13:27:15.726620Z digest=sha256:c6262e774b041374b5388aac0f9b2b72ab2063ae3e9c97031bbd829c1735477b

Observation 1113ae3b-c268-4ffe-aaa2-13d11241f9c0 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 50

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:18.842019Z

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.

source=pdf_text observed=2026-08-07T13:27:15.784434Z digest=sha256:47f9c2b56953e0c57daf4691122313f7121588b61912f6acab272e3b65fa0b95

Observation 9a10a2cd-d33b-4138-b202-42db516241c4 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 51

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:18.737602Z

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.

source=pdf_text observed=2026-08-07T13:27:15.864082Z digest=sha256:b3f3a8ff6c550756a7c20c102df8d67d32dabd25002a584aaec62fb58e379fc5

Observation 04cb29f6-8411-45d3-be50-b81659c7bccd · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 52

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:18.607236Z

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.

source=pdf_text observed=2026-08-07T13:27:15.953237Z digest=sha256:fd15dd99b7a295fec302c01daa2f12aca1598c242550d4df1b66960ecafbab73

Observation af252613-2fe3-4af9-a8eb-4cb77e2dc1ce · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 55

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:18.309930Z

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.

source=pdf_text observed=2026-08-07T13:27:16.326941Z digest=sha256:0b3d5b8af68cd0f92f49d142e921de1652b31d7631aa08cb3292d7cc7940d049

Observation e5f70394-e18e-45bb-9da8-c6a2c9b0f199 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 56

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:18.162798Z

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.

source=pdf_text observed=2026-08-07T13:27:16.426866Z digest=sha256:26b20b761d6514a17feb61ec25436af8987773942bff9270ce6c081e12a0e229

Observation dac513f5-766d-41d5-aef9-47a3c6b07eba · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 57

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:18.079103Z

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.

source=pdf_text observed=2026-08-07T13:27:16.490785Z digest=sha256:05c0eb682e18d242d93cb22eb22acc0abbd90711c141a748e23acc9220cd4ae8

Observation fcbea575-72f4-407e-9c16-4579287bdd1d · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 58

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:17.968752Z

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.

source=pdf_text observed=2026-08-07T13:27:16.572717Z digest=sha256:5fefc2f665a5941b7ad8ae513d4eafb47bc6193cf9b2b72ff80ddaa934753c52

Observation 40418a2e-741f-4293-a47d-8fa9812518d9 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 59

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:17.838032Z

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.

source=pdf_text observed=2026-08-07T13:27:16.683268Z digest=sha256:9b847f062f46832aee36155d2792fe42c4c024595a836e2610ecbfe6719fe3e5

Observation fc984470-2c07-4494-9c15-70d073d31376 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 60

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:17.719100Z

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.

source=pdf_text observed=2026-08-07T13:27:16.822719Z digest=sha256:cfae3b8dfc40641744949960bd8b0d22eb823b63c911d116edb3b02ef9e9b731

Observation 1de72851-fe62-4358-bfb6-2b0e90b9891b · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 61

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:17.603506Z

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.

source=pdf_text observed=2026-08-07T13:27:17.003664Z digest=sha256:c4dbe98e54bde3f8e61f271bcbef25c3adb8b6736cee52dad6f109e3aea66bc3

Observation 64fd508a-d127-4664-82a2-39cca7c6eb5c · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 62

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:17.496980Z

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.

source=pdf_text observed=2026-08-07T13:27:17.142847Z digest=sha256:b0a8dd64ae81998fb019eba230feba0b4bcc26bf994f13301c64db751ae5d76c

Observation 74761434-a26d-4678-b675-691e88b5e400 · outbound

This paper cites an unresolved cited work.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Unresolved cited work

Reference 63

Resolution
unresolved
raw_fallback, observed 2026-08-07T13:27:17.422836Z

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.

source=pdf_text observed=2026-08-07T13:27:17.181870Z digest=sha256:bf9ea3486269d0aff147ac6d448000db0641d964cfe5665fc795100d961a3944

Observation eb60f955-359b-44bb-bfb6-ca2a221c5044 · outbound

This paper cites AI safety via debate.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation AI safety via debate

Reference 2018

Resolution
unresolved
no resolver link, observed 2026-08-07T13:27:11.886133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:27:11.886133Z digest=sha256:dff123544848246b0bf3db9babaa217c17b543ac7ab0627b86fe8300d2de49bb

Observation ec1991b0-e46a-4526-aae5-152c8bd90df4 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Measuring Massive Multitask Language Understanding

Reference 2020

Resolution
unresolved
no resolver link, observed 2026-08-07T13:27:11.835042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:27:11.835042Z digest=sha256:2a2110e39757a6dfb1d9986d3d006f949ddfebf98c45d71c1efa6d8df452fff1

Observation 62b643ce-d5c1-4e7e-b656-f540c0034030 · outbound

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

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Reference 2022

Resolution
unresolved
no resolver link, observed 2026-08-07T13:27:12.080136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:27:12.080136Z digest=sha256:d050c52898391b19eb7704c34469713e6f285a0c6e4d1465ba22bbf06be084f1

Observation a68d59e7-708c-4bcf-bab5-35b8cfcb7ce5 · outbound

This paper cites OpenAI o1 System Card.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation OpenAI o1 System Card

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-07T13:27:11.984695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:27:11.984695Z digest=sha256:828e0419f17aafe4f0936f5ca450c390cbab0f20ec3d02a86f08e11e72d6daa6

Observation eac40eb2-99d1-43d6-9641-5364d8126918 · outbound

This paper cites Trading Inference-Time Compute for Adversarial Robustness.

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation Trading Inference-Time Compute for Adversarial Robustness

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-07T13:27:12.277081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T13:27:12.277081Z digest=sha256:403517f0428fa5c2ffb2d8e8fc463710e8312316e50b25b859d965db6252a753

Pith citing papers

No inbound Pith citation observations are available.