Paper Citation Record · LEDGER

Discrete JEPA: Learning Discrete Token Representations without Reconstruction

As of 9 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 0 inbound Pith citation observations for arXiv:2506.14373.

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

pith.paper-citation-record.v1
2506.14373 v2

Coverage vector

measured 47 of 47 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:24:30.453824Z

measured 47 of 47 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

47 of 47 outbound references displayed

verified exact0
verified fuzzy18
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9fc82712-be8b-4279-882b-ae724a91b7c6 · outbound

This paper cites write newline.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:26.185465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e57ea957-88f9-4c9f-90af-de864697285b · outbound

This paper cites Self-supervised learning from images with a joint-embedding predictive architecture.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Self-supervised learning from images with a joint-embedding predictive architecture

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:26.237674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee908e99-44c8-463c-bd17-ecc8f4bba974 · outbound

This paper cites FlexTok: Resampling Images into 1D Token Sequences of Flexible Length.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction FlexTok: Resampling Images into 1D Token Sequences of Flexible Length

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:26.329146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95fbd1b8-7cac-4aa6-bbf3-2814406a9c7b · outbound

This paper cites Dreamweaver: Learning compositional world models from pixels.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Dreamweaver: Learning compositional world models from pixels

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:34.007479Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7069b2c3-693c-47ea-b1fe-ec4da229b72d · outbound

This paper cites Data2vec: A general framework for self-supervised learning in speech, vision and language.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Data2vec: A general framework for self-supervised learning in speech, vision and language

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:33.995855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7da386d6-421f-44c2-9941-79ad399fe2b2 · outbound

This paper cites BEiT: BERT Pre-Training of Image Transformers.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction BEiT: BERT Pre-Training of Image Transformers

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:26.555325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f02d643-addc-4fe4-a12b-dd2f54dd7d74 · outbound

This paper cites VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:26.691304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 973f931b-ce4b-44e8-96b0-3e4cec9f4f07 · outbound

This paper cites V-jepa: Latent video prediction for visual representation learning.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction V-jepa: Latent video prediction for visual representation learning

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:33.985764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5448e556-3d81-4967-9691-4fb64c98e64b · outbound

This paper cites MC-JEPA: A Joint-Embedding Predictive Architecture for Self-Supervised Learning of Motion and Content Features.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction MC-JEPA: A Joint-Embedding Predictive Architecture for Self-Supervised Learning of Motion and Content Features

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:26.878798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 732a1c8b-1897-45ab-9cbc-572725cad9f4 · outbound

This paper cites an unresolved cited work.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:24:33.975553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e1dd3558-7b46-4bd9-982c-4cc91e50f13a · outbound

This paper cites Unsupervised learning of visual features by contrasting cluster assignments.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Unsupervised learning of visual features by contrasting cluster assignments

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:27.087183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7871b9f2-5379-45c5-a868-9ce7ff8dab8e · outbound

This paper cites Emerging properties in self-supervised vision transformers.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Emerging properties in self-supervised vision transformers

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:27.227869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 869ce1de-05c7-4f86-bb31-c3b5621ecd39 · outbound

This paper cites an unresolved cited work.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:27.320134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 970ba5bc-d4f8-44dc-8a9d-57e95e897a62 · outbound

This paper cites Denoising with a joint-embedding predictive architecture.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Denoising with a joint-embedding predictive architecture

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:33.941909Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 814a123c-9385-4331-9f15-c49a022cb99b · outbound

This paper cites Masked autoencoders are effective tokenizers for diffusion models.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Masked autoencoders are effective tokenizers for diffusion models

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:33.929950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4e342daa-260c-44e9-9c32-6d3b377521d8 · outbound

This paper cites A simple framework for contrastive learning of visual representations.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction A simple framework for contrastive learning of visual representations

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:33.775735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 797b6d33-8203-47ad-99bc-4d375504ee93 · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:27.663546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fda9560b-0e31-4ed5-b0ed-f4de325c639f · outbound

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

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Taming transformers for high-resolution image synthesis

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:27.763668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0cc2f58-a326-43cd-b30e-84fecd860496 · outbound

This paper cites an unresolved cited work.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:24:33.508791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 00540c91-095e-4b7b-8827-d9f08fba4a75 · outbound

This paper cites A-JEPA: Joint-Embedding Predictive Architecture Can Listen.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction A-JEPA: Joint-Embedding Predictive Architecture Can Listen

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:27.926611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bc71edd-e1c8-48cf-bdca-f54608716322 · outbound

This paper cites R., Blundell, C., Beaudoin, P., Heess, N., Mozer, M.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction R., Blundell, C., Beaudoin, P., Heess, N., Mozer, M

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:33.285288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 08e4475c-0384-4af4-86e4-73dbf9a9e974 · outbound

This paper cites Bootstrap your own latent-a new approach to self-supervised learning.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Bootstrap your own latent-a new approach to self-supervised learning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:28.070454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61cec8d4-1ce4-48d4-9469-a914b6f753d0 · outbound

This paper cites Momentum contrast for unsupervised visual representation learning.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Momentum contrast for unsupervised visual representation learning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:28.143370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2ba66fa-fa82-4785-9768-6d26e32b2d41 · outbound

This paper cites Masked autoencoders are scalable vision learners.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Masked autoencoders are scalable vision learners

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:33.018490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9a676a67-ffc9-485f-b242-4b3ccf2bb6bd · outbound

This paper cites Slot state space models.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Slot state space models

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:32.692226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2f9dff62-4992-4dc3-9889-0edbf6ebcdec · outbound

This paper cites Thinking, fast and slow.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Thinking, fast and slow

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:32.465421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e68e0ac9-b8b6-4158-bd8f-a754fcb4aa74 · outbound

This paper cites Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:28.604884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d73cb7f-299a-4e5b-b4d4-db1229f2358a · outbound

This paper cites A path towards autonomous machine intelligence version 0.9.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction A path towards autonomous machine intelligence version 0.9

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:32.146526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7e781f09-f75a-472e-a28a-00edc0b4d445 · outbound

This paper cites Autoregressive image generation using residual quantization.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Autoregressive image generation using residual quantization

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:31.956028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8ccd5c0d-d428-4790-84e5-a70538717b2c · outbound

This paper cites Finite Scalar Quantization: VQ-VAE Made Simple.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Finite Scalar Quantization: VQ-VAE Made Simple

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:28.960511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41008482-6f2f-4304-af53-592caea5d1ff · outbound

This paper cites an unresolved cited work.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:24:31.757430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5e3d6c9e-7bc1-4190-a1e8-d1af6e3499a7 · outbound

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

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Zero-shot text-to-image generation

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:31.604603Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 55338ea2-0bd6-481b-b711-77c34cfd078d · outbound

This paper cites Generating diverse high-fidelity images with vq-vae-2.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Generating diverse high-fidelity images with vq-vae-2

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:29.248985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b01dca9-4494-4488-be5c-3f2f370f5fb1 · outbound

This paper cites Neurosymbolic Grounding for Compositional World Models.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Neurosymbolic Grounding for Compositional World Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:29.359281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 843b2738-6ce8-4e95-a3f8-14f69bb196db · outbound

This paper cites Joint Embedding Predictive Architectures Focus on Slow Features.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Joint Embedding Predictive Architectures Focus on Slow Features

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:29.442876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2880a72-e37b-453e-a927-c5c302388e09 · outbound

This paper cites SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:29.539556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6f5fe50-fa18-43c0-be2a-d29adcd1bdf7 · outbound

This paper cites Worldcoder, a model-based llm agent: Building world models by writing code and interacting with the environment.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Worldcoder, a model-based llm agent: Building world models by writing code and interacting with the environment

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:29.651416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afa3f788-8206-42af-8017-d1fabb6caf6a · outbound

This paper cites and Levy, M.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction and Levy, M

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:31.447266Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4ed3b26e-65ec-436d-b75f-b7ea70d3e500 · outbound

This paper cites Neural discrete representation learning.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Neural discrete representation learning

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:29.801294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39fa1c7b-eed5-45d6-a9c7-6f4389ea56c5 · outbound

This paper cites LARP : Tokenizing videos with a learned autoregressive generative prior.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction LARP : Tokenizing videos with a learned autoregressive generative prior

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:31.292857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation dee467ee-a23f-4e91-85af-fc2a84316696 · outbound

This paper cites Spriteworld: A flexible, configurable reinforcement learning environment.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Spriteworld: A flexible, configurable reinforcement learning environment

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:31.074167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4af2eb45-a61b-43b3-89fb-ba0ebb81fea4 · outbound

This paper cites Towards Semantic Equivalence of Tokenization in Multimodal LLM.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Towards Semantic Equivalence of Tokenization in Multimodal LLM

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:30.005895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a426e9c4-71c3-4afb-a169-693f1fa86fb5 · outbound

This paper cites Temporally consistent transformers for video generation.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Temporally consistent transformers for video generation

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:30.096531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4b8d77e-2d40-4634-9e99-c9e758dae6fd · outbound

This paper cites Vector-quantized Image Modeling with Improved VQGAN.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction Vector-quantized Image Modeling with Improved VQGAN

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:30.154979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffb2c71a-d367-46f6-976a-014c9fc63ce1 · outbound

This paper cites G., Yang, M.-H., Hao, Y., Essa, I., et al.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction G., Yang, M.-H., Hao, Y., Essa, I., et al

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:30.921708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 314029b8-d81a-4696-bd4a-124ff8757640 · outbound

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

Discrete JEPA: Learning Discrete Token Representations without Reconstruction An image is worth 32 tokens for reconstruction and generation

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:30.337622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c8ddd92-360a-4c9e-9e87-a5c79cc23ca0 · outbound

This paper cites ibot: Image bert pre-training with online tokenizer.

Discrete JEPA: Learning Discrete Token Representations without Reconstruction ibot: Image bert pre-training with online tokenizer

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:30.751457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Pith citing papers

No inbound Pith citation observations are available.