Paper Citation Record · LEDGER

Training-Free Watermarking for Autoregressive Image Generation

As of 18 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 3 inbound Pith citation observations for arXiv:2505.14673.

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

pith.paper-citation-record.v1
2505.14673 v1

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:33:48.499614Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-30T10:28:59.577056Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-30T10:34:36.605549Z

Reference resolution

42 of 42 outbound references displayed

verified exact2
verified fuzzy10
unresolved30
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6278deea-6d8d-4039-8d64-337d7efd6460 · outbound

This paper cites Combined dwt-dct digital image watermarking.Journal of computer science, 3(9):740–746, 2007.

Training-Free Watermarking for Autoregressive Image Generation Combined dwt-dct digital image watermarking.Journal of computer science, 3(9):740–746, 2007

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:43.334734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d93f8f3c-7cb3-4f35-9dfd-0bebd04d15d3 · outbound

This paper cites Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901, 2020.

Training-Free Watermarking for Autoregressive Image Generation Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901, 2020

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:43.512135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 651e6a72-5ee3-41bb-9daf-2e4d4e95d65c · outbound

This paper cites The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation.

Training-Free Watermarking for Autoregressive Image Generation The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:43.680801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8fba076-67e4-4b5b-bb55-c2a2cdb1204d · outbound

This paper cites Reproducible scaling laws for contrastive language-image learning.

Training-Free Watermarking for Autoregressive Image Generation Reproducible scaling laws for contrastive language-image learning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:43.847198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1f6452b-bfd2-4bc8-b722-8d7303139276 · outbound

This paper cites Morgan kaufmann, 2007.

Training-Free Watermarking for Autoregressive Image Generation Morgan kaufmann, 2007

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:44.019969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdef4fc2-b879-4719-af2a-a3c4012aa28b · outbound

This paper cites Imagenet: A large- scale hierarchical image database.

Training-Free Watermarking for Autoregressive Image Generation Imagenet: A large- scale hierarchical image database

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:44.132806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf91de7f-5d40-4c48-bdc4-0f7a1172a1d4 · outbound

This paper cites Paths, trees, and flowers.Canadian Journal of mathematics, 17:449–467, 1965.

Training-Free Watermarking for Autoregressive Image Generation Paths, trees, and flowers.Canadian Journal of mathematics, 17:449–467, 1965

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:44.290828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f3c9e0d-ce70-443e-9d11-81b80b9adb59 · outbound

This paper cites Taming transformers for high-resolution image synthesis.

Training-Free Watermarking for Autoregressive Image Generation Taming transformers for high-resolution image synthesis

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:44.424451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61a0f4dd-3fec-487d-92ba-e4f52a462af1 · outbound

This paper cites John Wiley & Sons, 1991.

Training-Free Watermarking for Autoregressive Image Generation John Wiley & Sons, 1991

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:52.318213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f6b6fb7f-6868-4666-88b5-9a024e44c71b · outbound

This paper cites The sta- ble signature: Rooting watermarks in latent diffusion models.

Training-Free Watermarking for Autoregressive Image Generation The sta- ble signature: Rooting watermarks in latent diffusion models

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:52.053544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6f5dcc0f-2881-47b9-b994-9a0a0ebbde96 · outbound

This paper cites Improving Autoregressive Image Generation through Coarse-to-Fine Token Prediction.

Training-Free Watermarking for Autoregressive Image Generation Improving Autoregressive Image Generation through Coarse-to-Fine Token Prediction

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-08-07T15:33:49.409679Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a75ce0b5-e95a-4aff-9b5e-1c4da2e38a4b · outbound

This paper cites Gans trained by a two time-scale update rule converge to a local nash equilibrium.Advances in neural information processing systems, 30, 2017.

Training-Free Watermarking for Autoregressive Image Generation Gans trained by a two time-scale update rule converge to a local nash equilibrium.Advances in neural information processing systems, 30, 2017

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:44.937866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eddf57c5-aee6-4776-8572-eb60bcda8222 · outbound

This paper cites Denoising diffusion probabilistic models.Advances in neural information processing systems, 33:6840–6851, 2020.

Training-Free Watermarking for Autoregressive Image Generation Denoising diffusion probabilistic models.Advances in neural information processing systems, 33:6840–6851, 2020

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:45.054097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e35dfaf5-dc24-4630-b731-ed655de0b07c · outbound

This paper cites Improving Autoregressive Visual Generation with Cluster-Oriented Token Prediction.

Training-Free Watermarking for Autoregressive Image Generation Improving Autoregressive Visual Generation with Cluster-Oriented Token Prediction

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:45.200999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c92f8eb4-354e-4d26-81ed-96760bdc1433 · outbound

This paper cites Robin: Robust and invisible watermarks for diffusion models with adversarial optimization.Advances in Neural Information Processing Systems, 37:3937–3963, 2024.

Training-Free Watermarking for Autoregressive Image Generation Robin: Robust and invisible watermarks for diffusion models with adversarial optimization.Advances in Neural Information Processing Systems, 37:3937–3963, 2024

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:45.317674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e45fd87c-4e14-4a61-a151-6e3e86c1df8d · outbound

This paper cites White house rolls out plan to promote ethical ai, 2023.

Training-Free Watermarking for Autoregressive Image Generation White house rolls out plan to promote ethical ai, 2023

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:51.784434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c8b08e88-c499-40b4-bea6-8b5e4eea994d · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Training-Free Watermarking for Autoregressive Image Generation Adam: A Method for Stochastic Optimization

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:45.597539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fafaf2e2-4b41-4014-b8b8-98229f7d30ec · outbound

This paper cites A watermark for large language models.

Training-Free Watermarking for Autoregressive Image Generation A watermark for large language models

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:51.501829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d1d76832-697e-488c-91a6-85abfae86f1a · outbound

This paper cites Microsoft coco: Common objects in context.

Training-Free Watermarking for Autoregressive Image Generation Microsoft coco: Common objects in context

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:45.816667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35050779-3373-4db8-86c4-6890e908910d · outbound

This paper cites Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation.

Training-Free Watermarking for Autoregressive Image Generation Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:45.914528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34a1cf44-c923-4a66-ba13-a3985ea95340 · outbound

This paper cites Dwt- dct-svd based watermarking.

Training-Free Watermarking for Autoregressive Image Generation Dwt- dct-svd based watermarking

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:51.262429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 91f58445-e21d-41ec-a7fb-bc517c060a3c · outbound

This paper cites The maximum weight perfect matching problem for complete weighted graphs is in pc.

Training-Free Watermarking for Autoregressive Image Generation The maximum weight perfect matching problem for complete weighted graphs is in pc

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:51.075944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a1d5165f-e5d9-426c-a04f-1febc8fadbbb · outbound

This paper cites Learning transferable visual models from natural language supervision.

Training-Free Watermarking for Autoregressive Image Generation Learning transferable visual models from natural language supervision

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:46.199223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b59532f-f34d-47dd-996f-71433a912a69 · outbound

This paper cites Lawa: Using latent space for in-generation image watermarking.

Training-Free Watermarking for Autoregressive Image Generation Lawa: Using latent space for in-generation image watermarking

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:46.281619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f620d81-b008-4cbb-810a-723fe716375b · outbound

This paper cites Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation.

Training-Free Watermarking for Autoregressive Image Generation Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:46.445944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b0d2f80-4a9e-4ddb-b69f-a054c2a495e7 · outbound

This paper cites Visual autoregressive modeling: Scalable image generation via next-scale prediction.Advances in neural information processing systems, 37:84839–84865, 2024.

Training-Free Watermarking for Autoregressive Image Generation Visual autoregressive modeling: Scalable image generation via next-scale prediction.Advances in neural information processing systems, 37:84839–84865, 2024

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:46.539861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71f23ce2-86d3-41c4-93e3-42be2b9b9dbf · outbound

This paper cites Con- ditional image generation with pixelcnn decoders.Advances in neural information processing systems, 29, 2016.

Training-Free Watermarking for Autoregressive Image Generation Con- ditional image generation with pixelcnn decoders.Advances in neural information processing systems, 29, 2016

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:46.643654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ea778bc-ebdf-4905-97d7-73d642c8f4fc · outbound

This paper cites Pixel recurrent neural networks.

Training-Free Watermarking for Autoregressive Image Generation Pixel recurrent neural networks

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:46.772770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ae94214-a303-45fc-a3ad-3f1e477696be · outbound

This paper cites Neural discrete representation learning.Advances in neural information processing systems, 30, 2017.

Training-Free Watermarking for Autoregressive Image Generation Neural discrete representation learning.Advances in neural information processing systems, 30, 2017

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:46.931470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9df5b52c-41ff-491c-9e43-d201bc6c90cf · outbound

This paper cites Attention is all you need.Advances in neural information processing systems, 30, 2017.

Training-Free Watermarking for Autoregressive Image Generation Attention is all you need.Advances in neural information processing systems, 30, 2017

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:47.050511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccc888c2-c983-4af4-aeec-86d05c6ca0a5 · outbound

This paper cites An online propaganda campaign used ai-generated headshots to create fake journalists.V erge.

Training-Free Watermarking for Autoregressive Image Generation An online propaganda campaign used ai-generated headshots to create fake journalists.V erge

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:50.594564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b1932f1b-fd12-4318-9d77-6cabbca8ba69 · outbound

This paper cites Image quality assessment: from error visibility to structural similarity.IEEE transactions on image processing, 13(4):600– 612, 2004.

Training-Free Watermarking for Autoregressive Image Generation Image quality assessment: from error visibility to structural similarity.IEEE transactions on image processing, 13(4):600– 612, 2004

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:47.237779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7058cd2-5b8f-43e5-9ebc-65c8f41ae370 · outbound

This paper cites Safe-VAR: Safe Visual Autoregressive Model for Text-to-Image Generative Watermarking.

Training-Free Watermarking for Autoregressive Image Generation Safe-VAR: Safe Visual Autoregressive Model for Text-to-Image Generative Watermarking

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:47.357961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a37dccbd-b440-4fbb-b894-6dbcc1d9e281 · outbound

This paper cites Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust.

Training-Free Watermarking for Autoregressive Image Generation Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:47.493399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 817e9c4b-5ac3-4355-b71d-a4383e80d03f · outbound

This paper cites Microsoft pledges to watermark ai-generated images and videos, 2023.

Training-Free Watermarking for Autoregressive Image Generation Microsoft pledges to watermark ai-generated images and videos, 2023

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:50.316446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 52750fa7-4219-4f6f-bd4e-c73bfc1f3cb4 · outbound

This paper cites Wavelet transform based watermark for digital images.Optics Express, 3(12):497–511, 1998.

Training-Free Watermarking for Autoregressive Image Generation Wavelet transform based watermark for digital images.Optics Express, 3(12):497–511, 1998

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:50.049141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 41587b09-fb89-4c78-b0ab-a6827fe576b5 · outbound

This paper cites Responsible Disclosure of Generative Models Using Scalable Fingerprinting.

Training-Free Watermarking for Autoregressive Image Generation Responsible Disclosure of Generative Models Using Scalable Fingerprinting

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:47.936785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff21251c-d0dd-490f-a9d5-0d26c72c4448 · outbound

This paper cites An image is worth 32 tokens for reconstruction and generation.Advances in Neural Information Processing Systems, 37:128940–128966, 2024.

Training-Free Watermarking for Autoregressive Image Generation An image is worth 32 tokens for reconstruction and generation.Advances in Neural Information Processing Systems, 37:128940–128966, 2024

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:48.047309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4c459cc-eac1-4435-86ea-3eff3b4fc23f · outbound

This paper cites Robust Invisible Video Watermarking with Attention.

Training-Free Watermarking for Autoregressive Image Generation Robust Invisible Video Watermarking with Attention

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:48.147028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c760dc9-75eb-44e4-ba76-58565f1c71b2 · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

Training-Free Watermarking for Autoregressive Image Generation OPT: Open Pre-trained Transformer Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:48.270429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98e09bb5-8757-43ad-8f06-255ff2c9b328 · outbound

This paper cites Hidden: Hiding data with deep networks.

Training-Free Watermarking for Autoregressive Image Generation Hidden: Hiding data with deep networks

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:49.735110Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0960e20f-c130-465a-bff5-8b0c067f9b3e · outbound

This paper cites a photo of category.

Training-Free Watermarking for Autoregressive Image Generation a photo of category

Reference 43

Resolution: verified exact; raw_fallback, observed 2026-08-07T15:33:48.830738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

Observation 4fa2f5f2-5c67-4b47-8103-72345a85a971 · inbound

On the Robustness of Watermarking for Autoregressive Image Generation cites this paper.

On the Robustness of Watermarking for Autoregressive Image Generation Training-Free Watermarking for Autoregressive Image Generation

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:06:00.787284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b8a8272a-ba1e-4b82-bdbb-ee62653fda3a · inbound

Hidden in Plain Tokens: Simply Robust, Gradient-Free Watermark for Synthetic Audio cites this paper.

Hidden in Plain Tokens: Simply Robust, Gradient-Free Watermark for Synthetic Audio Training-Free Watermarking for Autoregressive Image Generation

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T23:14:01.883638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 995dae10-0008-4230-acea-974077a8d0ed · inbound

Data Provenance for Image Auto-Regressive Generation cites this paper.

Data Provenance for Image Auto-Regressive Generation Training-Free Watermarking for Autoregressive Image Generation

Reference 197

Resolution: verified exact; arxiv_id, observed 2026-06-30T10:34:36.606880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.