Paper Citation Record · LEDGER

AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking

As of 14 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2606.03347.

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

pith.paper-citation-record.v1
2606.03347 v1

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-28T11:10:52.856825Z

measured 15 of 15 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+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

15 of 15 outbound references displayed

verified exact1
verified fuzzy0
unresolved11
parse uncertain0
malformed identifier1
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 21110bc3-2cd5-409b-92ad-1523609b7111 · outbound

This paper cites Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs.

AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T02:06:27.685902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8a527844-f259-4227-86ad-a9d55915636f · outbound

This paper cites Mueller, M., Gruber, K., and Fok, D.

AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking Mueller, M., Gruber, K., and Fok, D

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-28T11:10:52.856825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db227f0a-bcdf-4728-95a2-21298b5812b0 · outbound

This paper cites MissDiff: Training Diffusion Models on Tabular Data with Missing Values.

AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking MissDiff: Training Diffusion Models on Tabular Data with Missing Values

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T02:06:27.692896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 92d98ead-cd03-41f0-9123-241d968527b9 · outbound

This paper cites Why Not to Use Zero Imputation? Correcting Sparsity Bias in Training Neural Networks.

AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking Why Not to Use Zero Imputation? Correcting Sparsity Bias in Training Neural Networks

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:06:27.688784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fc1521bf-379a-4797-85b5-7bd108202730 · outbound

This paper cites com/vanderschaarlab/hyperimpute, which fits pθ(xobs|z) and qγ(z|xobs) so that it can be refactored into a generative model.

AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking com/vanderschaarlab/hyperimpute, which fits pθ(xobs|z) and qγ(z|xobs) so that it can be refactored into a generative model

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-28T11:10:52.856825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3a06016-634b-46b8-bed8-9a385c8beeb1 · outbound

This paper cites To align the model size with other methods, we set batchsize to 64, diffusion embedding dim and timeembed to 1024, layers to 5, and channels to 256.

AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking To align the model size with other methods, we set batchsize to 64, diffusion embedding dim and timeembed to 1024, layers to 5, and channels to 256

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-28T11:10:52.856825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddbaae3d-6de6-498f-9d81-8fd451a44120 · outbound

This paper cites The default parameters (nt = 50, duplicateK = 100) did not converge within 3600 seconds.

AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking The default parameters (nt = 50, duplicateK = 100) did not converge within 3600 seconds

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-28T11:10:52.856825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a19802c-6195-4aee-ba0b-1bc5c5e90d30 · outbound

This paper cites The official implementation ( https://github.com/hengruizhang98/ DiffPuter) applies binary encoding for categorical variables, while the paper describes one-hot encoding.

AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking The official implementation ( https://github.com/hengruizhang98/ DiffPuter) applies binary encoding for categorical variables, while the paper describes one-hot encoding

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-28T11:10:52.856825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5f77c2b-63ac-4b6c-8040-1e754694ed08 · outbound

This paper cites In particular, we use 20 trees, δ = 0 and a minimum node size of 5.

AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking In particular, we use 20 trees, δ = 0 and a minimum node size of 5

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-28T11:10:52.856825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4f5a390-a67b-467c-afa6-a5f59e9d5695 · outbound

This paper cites For this model to work, the batch size must be divisible by 10.

AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking For this model to work, the batch size must be divisible by 10

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-28T11:10:52.856825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc17cb51-e3aa-468b-a3c4-9f8a92b203a8 · outbound

This paper cites We use a 256-dimensional embedding to better align the architecture with CTGAN, TabSyn and CDTD.

AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking We use a 256-dimensional embedding to better align the architecture with CTGAN, TabSyn and CDTD

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-28T11:10:52.856825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cf38cff-aeb5-41b1-b7c8-37b77e6f9da7 · outbound

This paper cites The training steps that go towards training the V AE and the denoising network follow the proportions given in the official code (see https://github.com/amazon-science/tabsyn).

AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking The training steps that go towards training the V AE and the denoising network follow the proportions given in the official code (see https://github.com/amazon-science/tabsyn)

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-28T11:10:52.856825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53827a4c-a643-42f1-b188-ab31b07ed5a0 · outbound

This paper cites We train for 30k steps with Adam (lr 2·10 −4) and EMA decay 0.999; sampling batch size is 2000.

AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking We train for 30k steps with Adam (lr 2·10 −4) and EMA decay 0.999; sampling batch size is 2000

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-28T11:10:52.856825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d058f90-972c-41af-913e-a74a8b5489f1 · outbound

This paper cites Diffusion uses 50 timesteps with EDM-style preconditioning (e.g., σmin = 0.002, σmax = 80, σdata = 1.0).

AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking Diffusion uses 50 timesteps with EDM-style preconditioning (e.g., σmin = 0.002, σmax = 80, σdata = 1.0)

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-28T11:10:52.856825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16576e5b-6e9b-46b7-ab4a-6f15e379b14b · outbound

This paper cites an unresolved cited work.

AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking Unresolved cited work

Reference 15

Resolution: malformed identifier; no resolver link, observed 2026-06-28T11:10:52.856825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.