Paper Citation Record · LEDGER

STAIR: Improving Safety Alignment with Introspective Reasoning

As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 16 inbound Pith citation observations for arXiv:2502.02384.

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

pith.paper-citation-record.v1
2502.02384 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 16 of 16 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 16 of 16 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:00:09.891654Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T08:55:35.501024Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 389ca17b-67fe-4ee1-a84b-4395171c63ce · inbound

Lifelong Safety Alignment for Language Models cites this paper.

Lifelong Safety Alignment for Language Models STAIR: Improving Safety Alignment with Introspective Reasoning

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:09.891654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a416ccbb-e87d-41e1-8d32-44294097d6bf · inbound

Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space cites this paper.

Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space STAIR: Improving Safety Alignment with Introspective Reasoning

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T13:36:00.906180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d46e43ee-3901-486a-9347-9043cb9922c4 · inbound

Jailbreak-R1: Exploring the Jailbreak Capabilities of LLMs via Reinforcement Learning cites this paper.

Jailbreak-R1: Exploring the Jailbreak Capabilities of LLMs via Reinforcement Learning STAIR: Improving Safety Alignment with Introspective Reasoning

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T12:01:10.437566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e41912e-1da9-4fb8-acd4-e0371b474a0a · inbound

A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents cites this paper.

A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents STAIR: Improving Safety Alignment with Introspective Reasoning

Reference 168

Resolution: unresolved; no resolver link, observed 2026-08-06T21:34:45.247292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac706d68-d974-483f-a88a-f08b92900242 · inbound

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning cites this paper.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning STAIR: Improving Safety Alignment with Introspective Reasoning

Reference 192

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.662094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d086361-f90d-4fe7-96af-0460dd52875d · inbound

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency cites this paper.

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency STAIR: Improving Safety Alignment with Introspective Reasoning

Reference 180

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T11:58:58.971164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7fc6467b-27c3-4ffb-a8a8-cfd20c6a6470 · inbound

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models cites this paper.

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models STAIR: Improving Safety Alignment with Introspective Reasoning

Reference 282

Resolution: unresolved; no resolver link, observed 2026-08-05T10:39:08.278123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc7a5628-d7d3-4cb6-90ee-a87cc183beb8 · inbound

Think Before You Code: Dual Reasoning for the NLSafety-Utility Trade-Off in LLM Code Generation cites this paper.

Think Before You Code: Dual Reasoning for the NLSafety-Utility Trade-Off in LLM Code Generation STAIR: Improving Safety Alignment with Introspective Reasoning

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:56:03.241384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0737ae2b-07de-4393-98fc-65a586ed0889 · inbound

Think Before You Code: Dual Reasoning for the NLSafety-Utility Trade-Off in LLM Code Generation cites this paper.

Think Before You Code: Dual Reasoning for the NLSafety-Utility Trade-Off in LLM Code Generation STAIR: Improving Safety Alignment with Introspective Reasoning

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-03T00:20:00.682943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b297c760-4626-49ed-b466-f4530ae1ee39 · inbound

Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment cites this paper.

Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment STAIR: Improving Safety Alignment with Introspective Reasoning

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:21:07.585694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation cc4bf590-040f-479a-9a48-56df55cf6195 · inbound

PriorZero: Bridging Language Priors and World Models for Decision Making cites this paper.

PriorZero: Bridging Language Priors and World Models for Decision Making STAIR: Improving Safety Alignment with Introspective Reasoning

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:27:18.588102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2d20f637-f108-4219-8c3e-2a3b6adf2909 · inbound

REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak cites this paper.

REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak STAIR: Improving Safety Alignment with Introspective Reasoning

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-21T06:19:41.987164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b0866cc7-3737-48fe-bd5f-8b63dcc85995 · inbound

MESA: Improving MoE Safety Alignment via Decentralized Expertise cites this paper.

MESA: Improving MoE Safety Alignment via Decentralized Expertise STAIR: Improving Safety Alignment with Introspective Reasoning

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-06-28T19:52:35.302215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6f213dd5-d7e9-4857-8646-da88fdcc71fb · inbound

Addressing Over-Refusal in LLMs with Competing Rewards cites this paper.

Addressing Over-Refusal in LLMs with Competing Rewards STAIR: Improving Safety Alignment with Introspective Reasoning

Reference 95

Resolution: verified exact; arxiv_id, observed 2026-07-01T08:55:35.502417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 06e04a08-3018-42c7-b4b1-24e4414d85e3 · inbound

UniNDM: A Unified Noise-driven Detection and Mitigation Framework Against Sexual Content in Text-to-Image Generation cites this paper.

UniNDM: A Unified Noise-driven Detection and Mitigation Framework Against Sexual Content in Text-to-Image Generation STAIR: Improving Safety Alignment with Introspective Reasoning

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-01T19:54:51.025596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 820d62e9-055a-458d-b2e8-4c39047555f2 · inbound

When Refusal Looks Safe: The Refusal-Cue Shortcut in Safety Guard Models cites this paper.

When Refusal Looks Safe: The Refusal-Cue Shortcut in Safety Guard Models STAIR: Improving Safety Alignment with Introspective Reasoning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-05T23:46:20.550587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.