Paper Citation Record · LEDGER

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering

As of 5 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2606.17257.

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

pith.paper-citation-record.v1
2606.17257 v1

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-27T03:44:36.071488Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+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

43 of 43 outbound references displayed

verified exact14
verified fuzzy0
unresolved28
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 37ee6826-1068-4a39-87ed-0dad5eab7dd6 · outbound

This paper cites Safesora: Towards safety alignment of text2video generation via a human preference dataset.Advances in Neural Information Processing Systems, 37:17161–17214, 2024.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Safesora: Towards safety alignment of text2video generation via a human preference dataset.Advances in Neural Information Processing Systems, 37:17161–17214, 2024

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 682dcb55-2036-4ebe-815f-df3f04b64984 · outbound

This paper cites Safewatch: An efficient safety-policy following video guardrail model with transparent explanations.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Safewatch: An efficient safety-policy following video guardrail model with transparent explanations

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c2d1ece-5c81-4183-bb37-58deb522dcee · outbound

This paper cites CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:48:45.925878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2554a1c4-8b72-4912-bafb-f77dfee9c955 · outbound

This paper cites Wan: Open and Advanced Large-Scale Video Generative Models.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Wan: Open and Advanced Large-Scale Video Generative Models

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:48:45.920148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation acfa9116-cc82-467c-8b07-463ced419999 · outbound

This paper cites Mochi 1.https://github.com/genmoai/models, 2024.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Mochi 1.https://github.com/genmoai/models, 2024

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 441bb7da-6663-46e9-ae45-b40a06771ca4 · outbound

This paper cites LTX-Video: Realtime Video Latent Diffusion.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering LTX-Video: Realtime Video Latent Diffusion

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:48:45.896437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1877b772-c90a-41dd-a3f5-0dfcea0f0edd · outbound

This paper cites Allegro: Open the Black Box of Commercial-Level Video Generation Model.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Allegro: Open the Black Box of Commercial-Level Video Generation Model

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-07-03T17:48:45.923563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6678c8ee-4c76-4df0-b2b3-7b150bb598c9 · outbound

This paper cites VideoGuard: Protecting Video Content from Unauthorized Editing.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering VideoGuard: Protecting Video Content from Unauthorized Editing

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-07-03T17:48:45.917684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1a573161-5b62-4eec-9edd-fb8bf6ec945c · outbound

This paper cites Sora by openai.https://openai.com/sora/, 2024.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Sora by openai.https://openai.com/sora/, 2024

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82cf8cc2-5cea-4cb6-afce-79aa6d724601 · outbound

This paper cites Text driven video generation.https://research.runwayml.com/gen2, 2023.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Text driven video generation.https://research.runwayml.com/gen2, 2023

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4ecee77-634a-45ee-8504-7c0cac5d7f65 · outbound

This paper cites Kling-Omni Technical Report.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Kling-Omni Technical Report

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:48:45.910408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 04453cd5-5eb9-4505-adda-7c43a1c49891 · outbound

This paper cites HunyuanVideo 1.5 Technical Report.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering HunyuanVideo 1.5 Technical Report

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:48:45.908421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a264c189-007d-4fa2-a001-9b75b909e63a · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:48:45.919945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8a0ca409-60c0-408d-8420-a4859ba3516c · outbound

This paper cites CoRR , volume =.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering CoRR , volume =

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T17:48:45.902229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3e629f36-ab41-480d-9b1c-6e26f0bfd220 · outbound

This paper cites Mma-diffusion: Multimodal attack on diffusion models.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Mma-diffusion: Multimodal attack on diffusion models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f846a9b-ccf3-45a5-8bb1-7429dd6060a8 · outbound

This paper cites A divide-and-conquer approach to distributed attack identification.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering A divide-and-conquer approach to distributed attack identification

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 508e50a8-f7bf-454a-a0cd-32d27c4895c5 · outbound

This paper cites Red-Teaming the Stable Diffusion Safety Filter.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Red-Teaming the Stable Diffusion Safety Filter

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-07-03T17:48:45.925768Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c0590099-bafb-414c-9c62-2058a2f09dbc · outbound

This paper cites Safegen: Mitigating sexually explicit content generation in text-to-image models.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Safegen: Mitigating sexually explicit content generation in text-to-image models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f54cd61e-1763-411b-8aa1-7ad15017a2a4 · outbound

This paper cites Supervised principal component analysis: Visualization, classification and regression on subspaces and submanifolds.Pattern Recognition, 44(7):1357–1371, 2011.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Supervised principal component analysis: Visualization, classification and regression on subspaces and submanifolds.Pattern Recognition, 44(7):1357–1371, 2011

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68fcc81a-3b3b-4173-9787-c536b5823a47 · outbound

This paper cites Polyjuice makes it real: Black-box, universal red teaming for synthetic image detectors.Advances in Neural Information Processing Systems, 2025.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Polyjuice makes it real: Black-box, universal red teaming for synthetic image detectors.Advances in Neural Information Processing Systems, 2025

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00d0fc7e-10a9-4c8f-9842-3a7a36b11862 · outbound

This paper cites Stable diffusion safety checker.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Stable diffusion safety checker

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb78d363-9da2-470a-9bc1-8697ff13d5a5 · outbound

This paper cites Erasing concepts from diffusion models.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Erasing concepts from diffusion models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ab99226-50c4-453f-bb78-910fbe2ab1a1 · outbound

This paper cites Unified concept editing in diffusion models.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Unified concept editing in diffusion models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c953be36-d2f6-4315-9c37-a9306822d20c · outbound

This paper cites Safe latent diffusion: Mitigating inappropriate degeneration in diffusion models.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Safe latent diffusion: Mitigating inappropriate degeneration in diffusion models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ef49fde-f947-4c0f-a661-3b22e4bbf9dc · outbound

This paper cites Self-discovering interpretable diffusion latent directions for responsible text-to-image generation.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Self-discovering interpretable diffusion latent directions for responsible text-to-image generation

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b686556-063e-4065-ba71-64023b06d588 · outbound

This paper cites Classifier-Free Diffusion Guidance.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Classifier-Free Diffusion Guidance

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:48:45.908054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 043fc93d-eadd-48fd-988e-b87d115d6032 · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Representation Engineering: A Top-Down Approach to AI Transparency

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:48:45.905410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 046e856b-f24d-4c22-87f2-ae409a7d78d7 · outbound

This paper cites Steering Language Models With Activation Engineering.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Steering Language Models With Activation Engineering

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:48:45.896648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 040631d5-44c5-4e2c-9cb9-8c007753b90d · outbound

This paper cites Refusal in language models is mediated by a single direction.Advances in Neural Information Processing Systems, 37:136037–136083, 2024.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Refusal in language models is mediated by a single direction.Advances in Neural Information Processing Systems, 37:136037–136083, 2024

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33627da3-412e-4383-9335-fba49cfbdac2 · outbound

This paper cites Measuring statistical dependence with hilbert-schmidt norms.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Measuring statistical dependence with hilbert-schmidt norms

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcff5d57-368c-42e1-97df-4afcc95aeb33 · outbound

This paper cites Improving video generation with human feedback.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Improving video generation with human feedback

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f3e2362-f3ac-4147-8cbf-9002169c711c · outbound

This paper cites LlamaFirewall: An open source guardrail system for building secure AI agents.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering LlamaFirewall: An open source guardrail system for building secure AI agents

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-07-03T17:48:45.928484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ae5a5bbd-1ef9-4a29-8016-78c0f59fe31e · outbound

This paper cites MMA-Diffusion: MultiModal Attack on Diffusion Models.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering MMA-Diffusion: MultiModal Attack on Diffusion Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b6e1794-828f-4ab6-b5c1-bccff588a88b · outbound

This paper cites Latent guard: a safety framework for text-to-image generation.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Latent guard: a safety framework for text-to-image generation

Reference 34

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6233e14-9828-4539-85e0-c1a1313cd304 · outbound

This paper cites Sneakyprompt: Jailbreaking text-to-image generative models.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Sneakyprompt: Jailbreaking text-to-image generative models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27519602-560b-42a8-a131-3fdc1b02aa07 · outbound

This paper cites T2vsafetybench: Evaluating the safety of text-to-video generative models.Advances in Neural Information Processing Systems, 37: 63858–63872, 2024.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering T2vsafetybench: Evaluating the safety of text-to-video generative models.Advances in Neural Information Processing Systems, 37: 63858–63872, 2024

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bcb7ed2-296b-403a-9082-60d51cc437ec · outbound

This paper cites Forget-me-not: Learning to forget in text-to-image diffusion models.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Forget-me-not: Learning to forget in text-to-image diffusion models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20cf3c7d-806f-41f2-b78e-e0dc6e9c9d92 · outbound

This paper cites Reliable and efficient concept erasure of text-to-image diffusion models.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Reliable and efficient concept erasure of text-to-image diffusion models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09a4b4c8-17b7-48ab-b53d-7d815f6b1a9b · outbound

This paper cites SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:48:45.928438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4037b647-08fd-49c2-a619-15ba988983ba · outbound

This paper cites The illusion of unlearning: The unstable nature of machine unlearning in text-to-image diffusion models.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering The illusion of unlearning: The unstable nature of machine unlearning in text-to-image diffusion models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 653519a8-04b9-4f40-9849-e41a5cb414c5 · outbound

This paper cites To generate or not? safety-driven unlearned diffusion models are still easy to generate unsafe images.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering To generate or not? safety-driven unlearned diffusion models are still easy to generate unsafe images

Reference 41

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d85c121-5b0d-4eba-bf76-ff4931d82878 · outbound

This paper cites Cambridge university press, 2012.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering Cambridge university press, 2012

Reference 42

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 236fbd36-4d10-4968-a827-48b9b53123a2 · outbound

This paper cites nudity” or “violence,.

Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering nudity” or “violence,

Reference 43

Resolution: unresolved; no resolver link, observed 2026-06-27T03:44:36.071488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.