{"as_of":"2026-08-14T21:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0df781f89721aa6b954f47d4d36c370b50a1c6c24581f5dda4ad8b79b6dd5633","coverage":[{"denominator":15,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":15,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-28T11:10:52.856825Z","state":"measured"},{"denominator":15,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":15,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2606.03347/citation-record","integrity":"/paper/2606.03347/integrity","json":"/paper/2606.03347/citation-record.json","paper":"/paper/2606.03347"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1706.02633","last_updated":"2017-12-04T04:31:38Z","snapshot_observed_at":"2026-08-14T20:55:16.543734Z","submitted_at":"2017-06-08T15:19:02Z","title":"Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs","version":2},"cited_work":{"arxiv_id":"1706.02633","doi":null,"metadata_source":"pith","pith_arxiv_id":"1706.02633","snapshot_observed_at":"2026-07-04T15:39:57.066588Z","title":"Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs","venue":"stat.ML","work_id":"46c80bfd-20e6-409b-9eb3-638ff1fdeb7a","year":2017},"citing_paper":{"arxiv_id":"2606.03347","last_updated":"2026-06-02T08:57:38Z","snapshot_observed_at":"2026-08-14T21:10:08.943788Z","submitted_at":"2026-06-02T08:57:38Z","title":"AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-28T11:10:52.856825Z"},"links":{"cited_paper":"/paper/1706.02633","citing_paper":"/paper/2606.03347"},"observation_digest":"sha256:b6e296eaf2923bc43a925995931adedc974c05320fd397e98cfe0afa7736d86c","observation_id":"21110bc3-2cd5-409b-92ad-1523609b7111","resolution":{"observed_at":"2026-07-02T02:06:27.685902Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T11:10:52.856825Z","title":"Mueller, M., Gruber, K., and Fok, D","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.03347","last_updated":"2026-06-02T08:57:38Z","snapshot_observed_at":"2026-08-14T21:10:08.943788Z","submitted_at":"2026-06-02T08:57:38Z","title":"AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-28T11:10:52.856825Z"},"links":{"citing_paper":"/paper/2606.03347"},"observation_digest":"sha256:f82cbd12472ded1c742b07245f2f9fc96215416d6ad9ef5873eb31c5e765477c","observation_id":"8a527844-f259-4227-86ad-a9d55915636f","resolution":{"observed_at":"2026-06-28T11:10:52.856825Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.00467","last_updated":"2023-07-02T03:49:47Z","snapshot_observed_at":"2026-08-13T11:04:25.644363Z","submitted_at":"2023-07-02T03:49:47Z","title":"MissDiff: Training Diffusion Models on Tabular Data with Missing Values","version":1},"cited_work":{"arxiv_id":"2307.00467","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2307.00467","snapshot_observed_at":"2026-07-02T06:56:44.796420Z","title":"Missdiff: Training dif- fusion models on tabular data with missing values","venue":null,"work_id":"283a6adc-60d8-4b48-93ce-3b7190cc6343","year":2023},"citing_paper":{"arxiv_id":"2606.03347","last_updated":"2026-06-02T08:57:38Z","snapshot_observed_at":"2026-08-14T21:10:08.943788Z","submitted_at":"2026-06-02T08:57:38Z","title":"AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-28T11:10:52.856825Z"},"links":{"cited_paper":"/paper/2307.00467","citing_paper":"/paper/2606.03347"},"observation_digest":"sha256:ab9d9323f732d36e821e4b803f716b4ad36e469e52c7a8a61746941b6ff180c0","observation_id":"db227f0a-bcdf-4728-95a2-21298b5812b0","resolution":{"observed_at":"2026-07-02T02:06:27.692896Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1906.00150","last_updated":"2020-02-06T08:43:31Z","snapshot_observed_at":"2026-08-14T16:22:41.364594Z","submitted_at":"2019-06-01T04:03:53Z","title":"Why Not to Use Zero Imputation? Correcting Sparsity Bias in Training Neural Networks","version":5},"cited_work":{"arxiv_id":"1906.00150","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1906.00150","snapshot_observed_at":"2026-07-02T02:06:27.687011Z","title":"Impute-then-scale,","venue":null,"work_id":"e9f0d248-0a16-4a97-8573-c4bd0b19e5b4","year":2021},"citing_paper":{"arxiv_id":"2606.03347","last_updated":"2026-06-02T08:57:38Z","snapshot_observed_at":"2026-08-14T21:10:08.943788Z","submitted_at":"2026-06-02T08:57:38Z","title":"AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-28T11:10:52.856825Z"},"links":{"cited_paper":"/paper/1906.00150","citing_paper":"/paper/2606.03347"},"observation_digest":"sha256:938d9a93ab9f15721a761a347a4a51b5400483a737b4cc5bea42c1960edef5a9","observation_id":"92d98ead-cd03-41f0-9123-241d968527b9","resolution":{"observed_at":"2026-07-02T02:06:27.688784Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T11:10:52.856825Z","title":"com/vanderschaarlab/hyperimpute, which fits pθ(xobs|z) and qγ(z|xobs) so that it can be refactored into a generative model","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.03347","last_updated":"2026-06-02T08:57:38Z","snapshot_observed_at":"2026-08-14T21:10:08.943788Z","submitted_at":"2026-06-02T08:57:38Z","title":"AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-28T11:10:52.856825Z"},"links":{"citing_paper":"/paper/2606.03347"},"observation_digest":"sha256:9f0bc4ae64091b21a64a2b045d7c94c9e2a9145a1d4c3d8b7b4ade22e2f08522","observation_id":"fc1521bf-379a-4797-85b5-7bd108202730","resolution":{"observed_at":"2026-06-28T11:10:52.856825Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T11:10:52.856825Z","title":"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","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.03347","last_updated":"2026-06-02T08:57:38Z","snapshot_observed_at":"2026-08-14T21:10:08.943788Z","submitted_at":"2026-06-02T08:57:38Z","title":"AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-28T11:10:52.856825Z"},"links":{"citing_paper":"/paper/2606.03347"},"observation_digest":"sha256:3531ddcf1a90a58dcd3aec7c63713bbcb23e40c0820583848043ffba889bd54e","observation_id":"c3a06016-634b-46b8-bed8-9a385c8beeb1","resolution":{"observed_at":"2026-06-28T11:10:52.856825Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T11:10:52.856825Z","title":"The default parameters (nt = 50, duplicateK = 100) did not converge within 3600 seconds","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.03347","last_updated":"2026-06-02T08:57:38Z","snapshot_observed_at":"2026-08-14T21:10:08.943788Z","submitted_at":"2026-06-02T08:57:38Z","title":"AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-28T11:10:52.856825Z"},"links":{"citing_paper":"/paper/2606.03347"},"observation_digest":"sha256:099afc73ec21c3e5774915e6565f1ab8de6d737d9bcd7b77380920e2ab4181d6","observation_id":"ddbaae3d-6de6-498f-9d81-8fd451a44120","resolution":{"observed_at":"2026-06-28T11:10:52.856825Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T11:10:52.856825Z","title":"The official implementation ( https://github.com/hengruizhang98/ DiffPuter) applies binary encoding for categorical variables, while the paper describes one-hot encoding","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.03347","last_updated":"2026-06-02T08:57:38Z","snapshot_observed_at":"2026-08-14T21:10:08.943788Z","submitted_at":"2026-06-02T08:57:38Z","title":"AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-28T11:10:52.856825Z"},"links":{"citing_paper":"/paper/2606.03347"},"observation_digest":"sha256:c7a70d8afa575e91e7af74e1de21b755b23d6c10f4436438c12f620533e58d1b","observation_id":"1a19802c-6195-4aee-ba0b-1bc5c5e90d30","resolution":{"observed_at":"2026-06-28T11:10:52.856825Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T11:10:52.856825Z","title":"In particular, we use 20 trees, δ = 0 and a minimum node size of 5","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.03347","last_updated":"2026-06-02T08:57:38Z","snapshot_observed_at":"2026-08-14T21:10:08.943788Z","submitted_at":"2026-06-02T08:57:38Z","title":"AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-28T11:10:52.856825Z"},"links":{"citing_paper":"/paper/2606.03347"},"observation_digest":"sha256:28f09298bdcd26bf165427c2253c38e6633f03ee9ff37ce78e41ca669dc24a81","observation_id":"f5f77c2b-63ac-4b6c-8040-1e754694ed08","resolution":{"observed_at":"2026-06-28T11:10:52.856825Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T11:10:52.856825Z","title":"For this model to work, the batch size must be divisible by 10","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.03347","last_updated":"2026-06-02T08:57:38Z","snapshot_observed_at":"2026-08-14T21:10:08.943788Z","submitted_at":"2026-06-02T08:57:38Z","title":"AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-28T11:10:52.856825Z"},"links":{"citing_paper":"/paper/2606.03347"},"observation_digest":"sha256:230fd4147a47575fb9d478c5ea371c36096854d1d9bb56ce84a85f7a9a17b228","observation_id":"f4f5a390-a67b-467c-afa6-a5f59e9d5695","resolution":{"observed_at":"2026-06-28T11:10:52.856825Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T11:10:52.856825Z","title":"We use a 256-dimensional embedding to better align the architecture with CTGAN, TabSyn and CDTD","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.03347","last_updated":"2026-06-02T08:57:38Z","snapshot_observed_at":"2026-08-14T21:10:08.943788Z","submitted_at":"2026-06-02T08:57:38Z","title":"AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-28T11:10:52.856825Z"},"links":{"citing_paper":"/paper/2606.03347"},"observation_digest":"sha256:f89362ccd490f22c38a55bd4a126e2c990c3d7fc22db92ff0d5ed01402d6846e","observation_id":"cc17cb51-e3aa-468b-a3c4-9f8a92b203a8","resolution":{"observed_at":"2026-06-28T11:10:52.856825Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T11:10:52.856825Z","title":"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)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.03347","last_updated":"2026-06-02T08:57:38Z","snapshot_observed_at":"2026-08-14T21:10:08.943788Z","submitted_at":"2026-06-02T08:57:38Z","title":"AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-28T11:10:52.856825Z"},"links":{"citing_paper":"/paper/2606.03347"},"observation_digest":"sha256:7225dc8c1bf580112739cd34819895321f89db7cebfbfffd7f1af28dc12f4f16","observation_id":"0cf38cff-aeb5-41b1-b7c8-37b77e6f9da7","resolution":{"observed_at":"2026-06-28T11:10:52.856825Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T11:10:52.856825Z","title":"We train for 30k steps with Adam (lr 2·10 −4) and EMA decay 0.999; sampling batch size is 2000","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.03347","last_updated":"2026-06-02T08:57:38Z","snapshot_observed_at":"2026-08-14T21:10:08.943788Z","submitted_at":"2026-06-02T08:57:38Z","title":"AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-28T11:10:52.856825Z"},"links":{"citing_paper":"/paper/2606.03347"},"observation_digest":"sha256:5ab0e5bf7cf3b27cc56890c6c7a4b4465a02a95e7470b92cd18dfce60abb71bb","observation_id":"53827a4c-a643-42f1-b188-ab31b07ed5a0","resolution":{"observed_at":"2026-06-28T11:10:52.856825Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T11:10:52.856825Z","title":"Diffusion uses 50 timesteps with EDM-style preconditioning (e.g., σmin = 0.002, σmax = 80, σdata = 1.0)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.03347","last_updated":"2026-06-02T08:57:38Z","snapshot_observed_at":"2026-08-14T21:10:08.943788Z","submitted_at":"2026-06-02T08:57:38Z","title":"AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-28T11:10:52.856825Z"},"links":{"citing_paper":"/paper/2606.03347"},"observation_digest":"sha256:12f394666726881b05f35ccaa99fa4b1bbd5355b4e8e031148aede3b022fc0d4","observation_id":"4d058f90-972c-41af-913e-a74a8b5489f1","resolution":{"observed_at":"2026-06-28T11:10:52.856825Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T11:10:52.856825Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.03347","last_updated":"2026-06-02T08:57:38Z","snapshot_observed_at":"2026-08-14T21:10:08.943788Z","submitted_at":"2026-06-02T08:57:38Z","title":"AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-28T11:10:52.856825Z"},"links":{"citing_paper":"/paper/2606.03347"},"observation_digest":"sha256:942d1121b6ba9832cd872a212ceff26a3e0998c0d7e720770f883119219e23f5","observation_id":"16576e5b-6e9b-46b7-ab4a-6f15e379b14b","resolution":{"observed_at":"2026-06-28T11:10:52.856825Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.03347","last_updated":"2026-06-02T08:57:38Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T21:10:08.943788Z","submitted_at":"2026-06-02T08:57:38Z","title":"AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking"},"reference_resolution":{"displayed":15,"state_counts":{"malformed_identifier":1,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":11,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":15},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"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."}