Paper Citation Record · LEDGER

SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 19 inbound Pith citation observations for arXiv:2406.12030.

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

pith.paper-citation-record.v1
2406.12030 v4

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 19 of 19 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 19 of 19 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T19:45:18.699387Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T01:36:25.477552Z

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 d2e12838-4ccf-49ba-9b17-e5e8a4b62372 · inbound

Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization cites this paper.

Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 117

Resolution: verified exact; arxiv_id, observed 2026-05-16T09:16:17.566890Z

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.

Observation 8d80368f-848e-46e4-ace1-a54ae02b4736 · inbound

A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations cites this paper.

A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T19:45:18.699387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83c036a9-1752-4c5d-9d45-0ad72cb60093 · inbound

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs cites this paper.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:26.196963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4094a705-1493-4f36-8a93-9f18872c12d1 · inbound

MDIT-Bench: Evaluating the Dual-Implicit Toxicity in Large Multimodal Models cites this paper.

MDIT-Bench: Evaluating the Dual-Implicit Toxicity in Large Multimodal Models SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T15:06:33.585160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20f30d17-d06d-43b2-b242-b28127eaadec · inbound

VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration cites this paper.

VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T14:13:13.206915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66eaf8e9-4a0e-441f-bf8c-28a6b5c608d6 · inbound

Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack cites this paper.

Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T13:22:02.983754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b2999f1-0081-45a8-8d5a-cf96aa11acf1 · inbound

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models cites this paper.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:17.144248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1db626b9-2698-4367-afcd-c3ca4ce1ee8d · inbound

Bootstrapping LLM Robustness for VLM Safety via Reducing the Pretraining Modality Gap cites this paper.

Bootstrapping LLM Robustness for VLM Safety via Reducing the Pretraining Modality Gap SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T12:37:22.450280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a5719e8-17ef-4d2f-994f-0806687c0102 · inbound

GThinker: Towards General Multimodal Reasoning via Cue-Guided Rethinking cites this paper.

GThinker: Towards General Multimodal Reasoning via Cue-Guided Rethinking SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-07T11:55:14.660602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa06ee05-0e53-492f-9fb9-e19e77971e5f · inbound

The Man Behind the Sound: Demystifying Audio Private Attribute Profiling via Multimodal Large Language Model Agents cites this paper.

The Man Behind the Sound: Demystifying Audio Private Attribute Profiling via Multimodal Large Language Model Agents SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-06T17:45:45.230207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffc2c45d-0465-46fb-a516-7373399e78f1 · inbound

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities cites this paper.

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:35.371849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d841a76a-6ab2-4fe8-8b92-cefda9142c5a · inbound

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs cites this paper.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.721119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08d7f4a5-692d-40ce-a274-cc75b88179e0 · inbound

Aligning Large Vision-Language Models by Deep Reinforcement Learning and Direct Preference Optimization cites this paper.

Aligning Large Vision-Language Models by Deep Reinforcement Learning and Direct Preference Optimization SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T23:11:33.026717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f44a7cbb-4b0b-474c-8a1b-1cb1de01c1be · inbound

A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data cites this paper.

A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 274

Resolution: unresolved; no resolver link, observed 2026-08-03T08:15:37.785906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5b84ebe-d63f-4aa0-bb8f-2e68e31372cd · inbound

AlignCultura: Towards Culturally Aligned Large Language Models? cites this paper.

AlignCultura: Towards Culturally Aligned Large Language Models? SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 124

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T12:56:04.792001Z

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.

Observation 8368717a-f511-4aad-8797-1c82f474b182 · inbound

Toward Native Multimodal Modeling: A Roadmap cites this paper.

Toward Native Multimodal Modeling: A Roadmap SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 145

Resolution: verified exact; arxiv_id, observed 2026-06-29T23:04:02.050551Z

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.

Observation 5b865bbb-0aaa-4bac-875f-a138a188ffb2 · inbound

Constitutional On-Policy Safe Distillation cites this paper.

Constitutional On-Policy Safe Distillation SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-07-02T01:36:25.479676Z

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.

Observation b2e385e7-cee5-4c69-be4b-fe72760b647b · inbound

Multimodal Reward Hacking in Reinforcement Learning cites this paper.

Multimodal Reward Hacking in Reinforcement Learning SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1f5fb41-b8fa-4e59-8cf2-210c92a0e195 · inbound

When Are Reasoning-Based Guardrails Not Efficient? ResponseGuard: A Fast Vision-Language Guard for Real-Time Moderation cites this paper.

When Are Reasoning-Based Guardrails Not Efficient? ResponseGuard: A Fast Vision-Language Guard for Real-Time Moderation SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T07:36:57.727029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.