Paper Citation Record · LEDGER

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge

As of 7 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 1 inbound Pith citation observation for arXiv:2508.00324.

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

pith.paper-citation-record.v1
2508.00324 v1

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T10:18:26.686397Z

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-25T23:37:49.412578Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-04T17:30:00.622652Z

Reference resolution

29 of 29 outbound references displayed

verified exact0
verified fuzzy0
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c2690ba0-7111-4ebd-b3f0-b6c72531ff4d · outbound

This paper cites an unresolved cited work.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-06T10:18:27.996788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 25df598f-45d3-4427-bdfd-463adfc71eab · outbound

This paper cites Evaluating Large Language Models Trained on Code.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge Evaluating Large Language Models Trained on Code

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:24.296351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99928bbd-a201-4d73-8f94-a9e0ae89fa79 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge Training Verifiers to Solve Math Word Problems

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:24.367710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63ce70aa-11b6-4875-8f83-7d9c8e29362a · outbound

This paper cites an unresolved cited work.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:24.405850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5a3d952-e6d6-49f3-a72c-8cf9204b488b · outbound

This paper cites Deliberative Alignment: Reasoning Enables Safer Language Models.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:24.466989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 169f18f3-c7f8-4951-acc6-b197dd78dc57 · outbound

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

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:24.526526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a352b9f5-de06-469f-b40d-07e19cea8e24 · outbound

This paper cites Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:24.586763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 282c23b5-9a8f-4599-acc0-f377b7f77596 · outbound

This paper cites an unresolved cited work.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-06T10:18:27.785881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 56d45a70-54e2-4893-8624-885b8fd276dc · outbound

This paper cites Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:24.777601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3491aa49-5990-4352-97d0-2b0d20a00cf0 · outbound

This paper cites an unresolved cited work.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:24.829088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3813ebaf-d21a-480e-955a-a77586ea0aec · outbound

This paper cites OpenAI o1 System Card.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge OpenAI o1 System Card

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:24.887219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95da808b-9f6f-439c-b054-0b6db5c73715 · outbound

This paper cites SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:24.965589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8516d96d-07f7-4324-a998-88a420aeb5dc · outbound

This paper cites an unresolved cited work.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-06T10:18:27.661356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4d6d1703-27a6-4005-ba2c-bd32f3a00ca1 · outbound

This paper cites an unresolved cited work.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:25.202097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5ca5ce9-3da0-471c-b728-7a9702899547 · outbound

This paper cites s1: Simple test-time scaling.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge s1: Simple test-time scaling

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:25.282728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fee9320a-6f73-4392-88dd-e22aaae91eb3 · outbound

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

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:25.385420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18f5d5f6-e434-480f-9c36-f15af4156978 · outbound

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

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:25.473811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 077607d6-89a4-4943-b341-4d1d0cd3ef9c · outbound

This paper cites A StrongREJECT for Empty Jailbreaks.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge A StrongREJECT for Empty Jailbreaks

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:25.592722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f062020-bac7-4c7c-8d06-74fc588d23f5 · outbound

This paper cites an unresolved cited work.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:25.690409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5d58cb8-17e3-48b1-933f-5a9d56d56b24 · outbound

This paper cites an unresolved cited work.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:25.798387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f4c8f8e-809e-438b-8126-b3bc6754e37e · outbound

This paper cites an unresolved cited work.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:25.883185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a452ff4-aec0-4560-81e1-dc39de49abfd · outbound

This paper cites SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:25.973754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9baf45b4-6b44-44e2-84f2-b7243c4134f7 · outbound

This paper cites R-TOFU: Unlearning in Large Reasoning Models.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge R-TOFU: Unlearning in Large Reasoning Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:26.115945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01dce2b2-92b8-4db2-ba16-40aefb5788d8 · outbound

This paper cites RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:26.207413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78132a7e-f53b-4d0c-b0f6-0771465e260a · outbound

This paper cites How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:26.329974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e7a4f2e-d2c6-4ecc-908a-b3159cc50641 · outbound

This paper cites an unresolved cited work.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:26.443904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61e4de22-82a8-4f38-85f4-f4d2e50d5d3f · outbound

This paper cites an unresolved cited work.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:26.512082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6df207fd-d5dc-40cf-a0ec-116e38c703b2 · outbound

This paper cites URL: " 'urlintro :=.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge URL: " 'urlintro :=

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:26.602669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 053cfe66-1469-4c3b-b4e7-0047f45465df · outbound

This paper cites write newline.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge write newline

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:26.686397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 5487ee9c-be80-44d9-85ea-e29142fd2aab · inbound

Do Thinking Tokens Help with Safety? cites this paper.

Do Thinking Tokens Help with Safety? R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-07-04T17:30:00.624437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.