Paper Citation Record · LEDGER

SafeCoT: Improving VLM Safety with Minimal Reasoning

As of 23 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 0 inbound Pith citation observations for arXiv:2506.08399.

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

pith.paper-citation-record.v1
2506.08399 v2

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:19:03.135029Z

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+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

30 of 30 outbound references displayed

verified exact1
verified fuzzy0
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4b0c5486-bbc8-409c-b926-e0efa45340f0 · outbound

This paper cites online" 'onlinestring :=.

SafeCoT: Improving VLM Safety with Minimal Reasoning online" 'onlinestring :=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T05:18:58.447395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dc06e14-60e3-42d2-9f42-60a8f1602c7c · outbound

This paper cites write newline.

SafeCoT: Improving VLM Safety with Minimal Reasoning write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T05:18:58.596158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66c3fe00-8eeb-44ae-b477-833153f107c4 · outbound

This paper cites Qwen2.5-VL Technical Report.

SafeCoT: Improving VLM Safety with Minimal Reasoning Qwen2.5-VL Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T05:18:58.728671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39c90310-def1-49ec-8075-9fecb2372120 · outbound

This paper cites Learn to Refuse: Making Large Language Models More Controllable and Reliable through Knowledge Scope Limitation and Refusal Mechanism.

SafeCoT: Improving VLM Safety with Minimal Reasoning Learn to Refuse: Making Large Language Models More Controllable and Reliable through Knowledge Scope Limitation and Refusal Mechanism

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T05:18:58.879055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffb19c7e-8dd3-409e-9bf5-36be12155848 · outbound

This paper cites an unresolved cited work.

SafeCoT: Improving VLM Safety with Minimal Reasoning Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T05:18:59.043525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c70559d-3381-4d10-b0b3-1897a35ec067 · outbound

This paper cites Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models.

SafeCoT: Improving VLM Safety with Minimal Reasoning Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T05:18:59.175848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 581de71d-6376-4c8a-92b5-3299962b3318 · outbound

This paper cites ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting.

SafeCoT: Improving VLM Safety with Minimal Reasoning ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-08-07T05:19:03.832298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d3887f60-c7e8-49ca-b717-bf18f935a22d · outbound

This paper cites OR-Bench: An Over-Refusal Benchmark for Large Language Models.

SafeCoT: Improving VLM Safety with Minimal Reasoning OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T05:18:59.574137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dca78e86-4798-4ca6-9d8d-14d1da8af2b1 · outbound

This paper cites an unresolved cited work.

SafeCoT: Improving VLM Safety with Minimal Reasoning Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:19:04.755134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3b785fb5-6bea-4a46-8a49-46ff254e8335 · outbound

This paper cites The Llama 3 Herd of Models.

SafeCoT: Improving VLM Safety with Minimal Reasoning The Llama 3 Herd of Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T05:18:59.894827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d690aabc-7d87-4f24-929f-34c3c953e1ee · outbound

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

SafeCoT: Improving VLM Safety with Minimal Reasoning Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T05:19:00.051825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 322ccb29-c7ea-4610-89b9-e66eff1e6f74 · outbound

This paper cites POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization.

SafeCoT: Improving VLM Safety with Minimal Reasoning POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T05:19:00.170710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18e04e00-761f-434a-9e7c-d063336e6284 · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

SafeCoT: Improving VLM Safety with Minimal Reasoning LLaVA-OneVision: Easy Visual Task Transfer

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T05:19:00.298358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75b7782f-f2db-4a91-b4bd-66b99c8b9fcd · outbound

This paper cites an unresolved cited work.

SafeCoT: Improving VLM Safety with Minimal Reasoning Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T05:19:00.434399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e537bd8-3e1b-4e0f-b7fe-f9a54b31006e · outbound

This paper cites an unresolved cited work.

SafeCoT: Improving VLM Safety with Minimal Reasoning Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T05:19:00.577318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ead23f03-ad26-4c20-9ad5-a69187c4afd6 · outbound

This paper cites Safety Alignment for Vision Language Models.

SafeCoT: Improving VLM Safety with Minimal Reasoning Safety Alignment for Vision Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T05:19:00.692234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d035739-bf70-455c-97b0-f12d6b628075 · outbound

This paper cites SmolVLM: Redefining small and efficient multimodal models.

SafeCoT: Improving VLM Safety with Minimal Reasoning SmolVLM: Redefining small and efficient multimodal models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T05:19:00.833026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9ab3634-ce5c-463f-ad95-31422164fb68 · outbound

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

SafeCoT: Improving VLM Safety with Minimal Reasoning XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T05:19:01.034173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation beae7e52-ef44-4a6d-b144-61eb5fb08406 · outbound

This paper cites Selective "Selective Prediction": Reducing Unnecessary Abstention in Vision-Language Reasoning.

SafeCoT: Improving VLM Safety with Minimal Reasoning Selective "Selective Prediction": Reducing Unnecessary Abstention in Vision-Language Reasoning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T05:19:01.236803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dfa522f-e536-4f4a-b6ea-4f07f49b378f · outbound

This paper cites Gemma 3 Technical Report.

SafeCoT: Improving VLM Safety with Minimal Reasoning Gemma 3 Technical Report

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T05:19:01.429950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33c437f8-7b8e-4322-9149-403ae7c69b4d · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

SafeCoT: Improving VLM Safety with Minimal Reasoning Gemma 2: Improving Open Language Models at a Practical Size

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T05:19:01.612998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 718af07d-d334-47eb-83bc-324ef27c76c5 · outbound

This paper cites Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models.

SafeCoT: Improving VLM Safety with Minimal Reasoning Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T05:19:01.768974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3191c6e-2158-4cc5-bc20-5a1ee6f62eee · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

SafeCoT: Improving VLM Safety with Minimal Reasoning Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T05:19:01.936332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07b98d38-3d6e-4939-ac4b-f675ced178b6 · outbound

This paper cites an unresolved cited work.

SafeCoT: Improving VLM Safety with Minimal Reasoning Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:19:04.401406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 97f0fcf6-060a-4382-81ee-d4758aa61b3d · outbound

This paper cites an unresolved cited work.

SafeCoT: Improving VLM Safety with Minimal Reasoning Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T05:19:02.341674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80a4ecf4-2cca-4d8e-bed9-41be599adae0 · outbound

This paper cites an unresolved cited work.

SafeCoT: Improving VLM Safety with Minimal Reasoning Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:19:04.125304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a58398f4-79b8-4b32-8d86-a01a50d3b514 · outbound

This paper cites SafetyBench: Evaluating the Safety of Large Language Models.

SafeCoT: Improving VLM Safety with Minimal Reasoning SafetyBench: Evaluating the Safety of Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T05:19:02.714368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d88b1bd4-184d-4ee8-94b1-adea27547ae8 · outbound

This paper cites Looking Beyond Text: Reducing Language bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance.

SafeCoT: Improving VLM Safety with Minimal Reasoning Looking Beyond Text: Reducing Language bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T05:19:02.843411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e806e8d-2bb6-4740-bf5a-049e67f15c8b · outbound

This paper cites Multimodal Situational Safety.

SafeCoT: Improving VLM Safety with Minimal Reasoning Multimodal Situational Safety

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T05:19:02.992699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c719f41e-3446-4332-a95f-81823d9e87a4 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

SafeCoT: Improving VLM Safety with Minimal Reasoning Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T05:19:03.135029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.