Paper Citation Record · LEDGER

Highly Compressed Tokenizer Can Generate Without Training

As of 19 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 4 inbound Pith citation observations for arXiv:2506.08257.

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

pith.paper-citation-record.v1
2506.08257 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:20:33.559040Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-28T10:44:24.318786Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

41 of 41 outbound references displayed

verified exact0
verified fuzzy28
unresolved13
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 16ef8461-5182-4194-a6da-b794a777eaa2 · outbound

This paper cites write newline.

Highly Compressed Tokenizer Can Generate Without Training write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T05:20:30.399891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2841993-cece-482b-94bb-4dc7bb384bb6 · outbound

This paper cites Why are conditional generative models better than unconditional ones? In NeurIPS 2022 Workshop on Score-Based Methods, 2022.

Highly Compressed Tokenizer Can Generate Without Training Why are conditional generative models better than unconditional ones? In NeurIPS 2022 Workshop on Score-Based Methods, 2022

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:38.351781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a944599e-2bf5-45d4-9fca-16a1c40ae1e3 · outbound

This paper cites Retrieval-augmented diffusion models.

Highly Compressed Tokenizer Can Generate Without Training Retrieval-augmented diffusion models

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:38.336162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation eda6c2c0-d3c4-4491-8eb5-479228ce9b1e · outbound

This paper cites High fidelity visualization of what your self-supervised representation knows about.

Highly Compressed Tokenizer Can Generate Without Training High fidelity visualization of what your self-supervised representation knows about

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:38.318753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 27dc9c4b-6dbe-41f6-8039-cf34e9895efc · outbound

This paper cites Efficient-VQGAN : Towards high-resolution image generation with efficient vision transformers.

Highly Compressed Tokenizer Can Generate Without Training Efficient-VQGAN : Towards high-resolution image generation with efficient vision transformers

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:38.303443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 62e717e5-4fb7-4f19-a948-a86c5ff0814d · outbound

This paper cites Instance-conditioned GAN.

Highly Compressed Tokenizer Can Generate Without Training Instance-conditioned GAN

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:38.287286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7051860a-9774-4dc8-8090-5f610e8d39b1 · outbound

This paper cites an unresolved cited work.

Highly Compressed Tokenizer Can Generate Without Training Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:20:38.272768Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b0f08a11-acee-419d-a058-bf175aa68da0 · outbound

This paper cites VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance.

Highly Compressed Tokenizer Can Generate Without Training VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T05:20:30.863466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53434fb0-2c25-4d62-8e0e-799327489cf5 · outbound

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

Highly Compressed Tokenizer Can Generate Without Training ImageNet : A large-scale hierarchical image database

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:38.256220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 66a1f18d-4358-43a5-8f0a-c69a0815d1ab · outbound

This paper cites and Nichol, A.

Highly Compressed Tokenizer Can Generate Without Training and Nichol, A

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T05:20:31.000262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32b8c263-82ef-49e9-9559-8bca00f5122e · outbound

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

Highly Compressed Tokenizer Can Generate Without Training Taming transformers for high-resolution image synthesis

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:38.230564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3e4b0dd7-a5c2-4cf0-803f-195574672eb4 · outbound

This paper cites H., Chechik, G., and Cohen-Or, D.

Highly Compressed Tokenizer Can Generate Without Training H., Chechik, G., and Cohen-Or, D

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:38.214950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d5a1c10b-e5cc-46f7-a869-7a357c68bb8c · outbound

This paper cites Generating images from caption and vice versa via CLIP -guided generative latent space search.

Highly Compressed Tokenizer Can Generate Without Training Generating images from caption and vice versa via CLIP -guided generative latent space search

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:38.199309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 54dc9eab-4240-4cc5-b363-a19128154dd4 · outbound

This paper cites GANs trained by a two time-scale update rule converge to a local nash equilibrium.

Highly Compressed Tokenizer Can Generate Without Training GANs trained by a two time-scale update rule converge to a local nash equilibrium

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:38.182456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 580eb988-de0a-4f59-a6d3-548eab69fe4d · outbound

This paper cites an unresolved cited work.

Highly Compressed Tokenizer Can Generate Without Training Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T05:20:31.307672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7e625df-e501-4687-86fe-f6947afdbf39 · outbound

This paper cites Return of unconditional generation: A self-supervised representation generation method.

Highly Compressed Tokenizer Can Generate Without Training Return of unconditional generation: A self-supervised representation generation method

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:38.156129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation eb8eee19-4730-45c5-8ba8-53f15d612ae1 · outbound

This paper cites Autoregressive image generation without vector quantization.

Highly Compressed Tokenizer Can Generate Without Training Autoregressive image generation without vector quantization

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T05:20:31.406422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab85bd8f-845e-44ab-82e2-f586c2d4fc7c · outbound

This paper cites Challenging common assumptions in the unsupervised learning of disentangled representations.

Highly Compressed Tokenizer Can Generate Without Training Challenging common assumptions in the unsupervised learning of disentangled representations

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:37.920846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation df791c3a-65c3-4929-8040-aa235491df21 · outbound

This paper cites Finite scalar quantization: Vq-vae made simple.

Highly Compressed Tokenizer Can Generate Without Training Finite scalar quantization: Vq-vae made simple

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:37.691027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e7ec8fb5-af7f-41b4-b33b-0bb2d87eeb7f · outbound

This paper cites Styleclip: Text-driven manipulation of stylegan imagery.

Highly Compressed Tokenizer Can Generate Without Training Styleclip: Text-driven manipulation of stylegan imagery

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:37.360258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 78d31d65-f719-47e4-b946-3a852c97270b · outbound

This paper cites and Xie, S.

Highly Compressed Tokenizer Can Generate Without Training and Xie, S

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T05:20:31.684542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2722306-e96f-4dee-89c4-1cd24b734266 · outbound

This paper cites W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al.

Highly Compressed Tokenizer Can Generate Without Training W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T05:20:31.790839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5904539a-6718-4864-9e08-5cb53dac7fa9 · outbound

This paper cites Zero-shot text-to-image generation.

Highly Compressed Tokenizer Can Generate Without Training Zero-shot text-to-image generation

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:37.124661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0dbfa4f7-4d1f-4c4c-a045-00fe808c7fd6 · outbound

This paper cites DynamicViT : Efficient vision transformers with dynamic token sparsification.

Highly Compressed Tokenizer Can Generate Without Training DynamicViT : Efficient vision transformers with dynamic token sparsification

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:36.859164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5960a89f-84ff-4773-860c-de27e5877901 · outbound

This paper cites Generating diverse high-fidelity images with VQ-VAE-2.

Highly Compressed Tokenizer Can Generate Without Training Generating diverse high-fidelity images with VQ-VAE-2

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:36.689899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8fc58433-f568-4061-82a2-47025a9899e6 · outbound

This paper cites High-resolution image synthesis with latent diffusion models.

Highly Compressed Tokenizer Can Generate Without Training High-resolution image synthesis with latent diffusion models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T05:20:32.108976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91b4e0a7-42fc-4535-bb8f-14fa3690cf45 · outbound

This paper cites Improved techniques for training GANs.

Highly Compressed Tokenizer Can Generate Without Training Improved techniques for training GANs

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:36.432216Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation aee17a2c-1d2e-4484-9c73-6635508ab989 · outbound

This paper cites Image synthesis with a single (robust) classifier.

Highly Compressed Tokenizer Can Generate Without Training Image synthesis with a single (robust) classifier

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:36.219471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ca19b30b-ef8c-4866-81ca-de882c9d7aec · outbound

This paper cites KNN-Diffusion : Image generation via large-scale retrieval.

Highly Compressed Tokenizer Can Generate Without Training KNN-Diffusion : Image generation via large-scale retrieval

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:35.892169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8c9dc712-c644-4933-98de-fe40710e92a7 · outbound

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

Highly Compressed Tokenizer Can Generate Without Training Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T05:20:32.375413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68aaf7aa-668e-422e-b535-5eccf2854af2 · outbound

This paper cites ADDP : Learning general representations for image recognition and generation with alternating denoising diffusion process.

Highly Compressed Tokenizer Can Generate Without Training ADDP : Learning general representations for image recognition and generation with alternating denoising diffusion process

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:35.622605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4a21e32e-e6b8-459a-a42f-484b364885d9 · outbound

This paper cites Neural discrete representation learning.

Highly Compressed Tokenizer Can Generate Without Training Neural discrete representation learning

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T05:20:32.607625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9743a2c-40f9-4fa4-a29b-86f0ab179a18 · outbound

This paper cites Visual lexicon: Rich image features in language space.

Highly Compressed Tokenizer Can Generate Without Training Visual lexicon: Rich image features in language space

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:35.373678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 976a7ef7-fa83-4657-bb4d-d884df9f23f7 · outbound

This paper cites Show-o: One Single Transformer to Unify Multimodal Understanding and Generation.

Highly Compressed Tokenizer Can Generate Without Training Show-o: One Single Transformer to Unify Multimodal Understanding and Generation

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T05:20:32.840889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d49759b-8e7c-4a91-be9c-294f50428eb3 · outbound

This paper cites Y., Zhang, H., Pang, R., Qin, J., Ku, A., Xu, Y., Baldridge, J., and Wu, Y.

Highly Compressed Tokenizer Can Generate Without Training Y., Zhang, H., Pang, R., Qin, J., Ku, A., Xu, Y., Baldridge, J., and Wu, Y

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:35.092014Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 093d3f2c-7256-4cac-a003-9f1b702dfc56 · outbound

This paper cites B., Versari, L., Sohn, K., Minnen, D., Cheng, Y., Birodkar, V., Gupta, A., Gu, X., Hauptmann, A.

Highly Compressed Tokenizer Can Generate Without Training B., Versari, L., Sohn, K., Minnen, D., Cheng, Y., Birodkar, V., Gupta, A., Gu, X., Hauptmann, A

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:34.857050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 840a6b0f-6826-4586-b612-c6faef8f5df4 · outbound

This paper cites An image is worth 32 tokens for reconstruction and generation.

Highly Compressed Tokenizer Can Generate Without Training An image is worth 32 tokens for reconstruction and generation

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:34.587102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation bde1ae00-09c5-48bd-977e-419dcb7c348a · outbound

This paper cites Sigmoid loss for language image pre-training.

Highly Compressed Tokenizer Can Generate Without Training Sigmoid loss for language image pre-training

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:34.329879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2cb8bb48-33f3-42d0-87d7-1adfb5265624 · outbound

This paper cites A., Shechtman, E., and Wang, O.

Highly Compressed Tokenizer Can Generate Without Training A., Shechtman, E., and Wang, O

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T05:20:33.361815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcffc91c-2b2c-4a81-bab5-eaa0bfe7855f · outbound

This paper cites Transfusion: Predict the next token and diffuse images with one multi-modal model.

Highly Compressed Tokenizer Can Generate Without Training Transfusion: Predict the next token and diffuse images with one multi-modal model

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:34.079846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 26cf7926-9be0-4252-b2a1-0c3061d7342b · outbound

This paper cites Shifted diffusion for text-to-image generation.

Highly Compressed Tokenizer Can Generate Without Training Shifted diffusion for text-to-image generation

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:20:33.818240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Pith citing papers

Observation 47b10b4d-d5be-4f53-92fc-d1d8cd914d70 · inbound

Diffusing in the Right Space: A Systematic Study of Latent Diffusability cites this paper.

Diffusing in the Right Space: A Systematic Study of Latent Diffusability Highly Compressed Tokenizer Can Generate Without Training

Reference 85

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:36:27.606412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2c151745-7ad7-4c49-998e-0b0fa5c660bc · inbound

Balancing Image Compression and Generation with Bootstrapped Tokenization cites this paper.

Balancing Image Compression and Generation with Bootstrapped Tokenization Highly Compressed Tokenizer Can Generate Without Training

Reference 27

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T11:46:55.447804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation abe6c91c-83f8-417f-bce3-b56488f3a6d8 · inbound

Continuous Language Diffusion as a Decoder-Interface Problem cites this paper.

Continuous Language Diffusion as a Decoder-Interface Problem Highly Compressed Tokenizer Can Generate Without Training

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-06-27T18:31:07.705436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation df3d494b-7bc8-46ce-a6f7-bac05d6eaea1 · inbound

TivTok: Broadcasting Time-Invariant Tokens for Scalable Video Tokenization cites this paper.

TivTok: Broadcasting Time-Invariant Tokens for Scalable Video Tokenization Highly Compressed Tokenizer Can Generate Without Training

Reference 95

Resolution: verified exact; arxiv_id, observed 2026-07-03T20:28:55.554344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.