{"as_of":"2026-08-21T17:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:96beeff6567ac7f2fefab54d527607049a3f97a5c264e40a185d6df7640400aa","coverage":[{"denominator":29,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":29,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T16:47:59.197683Z","state":"measured"},{"denominator":29,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":29,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+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/2412.09842/citation-record","integrity":"/paper/2412.09842/integrity","json":"/paper/2412.09842/citation-record.json","paper":"/paper/2412.09842"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:47:59.758019Z","title":"Differential privacy,","venue":null,"work_id":"80d2da22-8276-4d19-9014-a90524b92354","year":2006},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.065135Z"},"links":{"citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:51be63ed3418c18003172be21d4416ad03930c74947b0c6732cedcdf647b5cd5","observation_id":"72b01606-c95c-4e98-b0cd-802cf03c7b4f","resolution":{"observed_at":"2026-08-11T16:47:59.763293Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:47:59.738936Z","title":"In-distribution public data synthesis with diffusion models for differentially private image classification,","venue":null,"work_id":"df4b7c03-2851-4543-bc78-120843df634a","year":2024},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.070247Z"},"links":{"citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:3c62836235eddbe15b2ff64f7a052faba2113a9295c5541e5a21f3984dce91b1","observation_id":"77fb6d08-f159-4f42-b380-4ef920d48e19","resolution":{"observed_at":"2026-08-11T16:47:59.745004Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.13650","last_updated":"2022-06-16T17:47:42Z","snapshot_observed_at":"2026-08-16T17:03:52.960553Z","submitted_at":"2022-04-28T17:10:56Z","title":"Unlocking High-Accuracy Differentially Private Image Classification through Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.13650","snapshot_observed_at":"2026-08-11T16:47:59.075516Z","title":"Unlocking high-accuracy differentially pri- vate image classification through scale,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.075516Z"},"links":{"cited_paper":"/paper/2204.13650","citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:1615373f18238ce624f5c97a469313cf0b36c41bb7ff02bd20cf76889fbfdb6f","observation_id":"99d6cf8b-b34d-4cb9-a95a-459f9d8face1","resolution":{"observed_at":"2026-08-11T16:47:59.075516Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:47:59.715847Z","title":"Position: Consid- erations for differentially private learning with large-scale public pretraining,","venue":null,"work_id":"eb5d7c61-529d-4f3d-a3d5-79d305f4f6b2","year":2022},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.080507Z"},"links":{"citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:c227ec739e6e3201ed9541af3efab899ffb401174ba8560a134ac01507f6b3cf","observation_id":"87e62ce6-a476-4359-807e-086610937d1a","resolution":{"observed_at":"2026-08-11T16:47:59.723812Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:47:59.697033Z","title":"Dif- ferentially Private Diffusion Models,","venue":null,"work_id":"22e14d45-9096-49c6-9f82-639630173c6f","year":2023},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.085495Z"},"links":{"citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:76ed7996d2f6b8b4eb103e2a0014b1589faf141655d44d275c3ece817a0cfce0","observation_id":"6c0721d7-99c0-4ba2-b7bd-063dfc32ec09","resolution":{"observed_at":"2026-08-11T16:47:59.701667Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:47:59.681998Z","title":"Learning to see by looking at noise,","venue":null,"work_id":"1a521b9d-9a4f-4386-a59a-b3cc85b80f86","year":2021},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.089988Z"},"links":{"citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:0b9a2bf82f7fbd9ac6d768c67606f9e768fe2fdaf6ab4c704e0412e406d557c0","observation_id":"a5c7f0ae-7037-4c4b-8fcc-20bb905e8c1c","resolution":{"observed_at":"2026-08-11T16:47:59.686269Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:47:59.665851Z","title":"Differ- entially private image classification by learning priors from random processes,","venue":null,"work_id":"04f428a2-a3ac-43e2-8192-2da7af42aaa0","year":2024},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.094934Z"},"links":{"citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:3b02a120675bd434c8a96acdd5451146606650f1dbf6d6c05d609cba8e784664","observation_id":"ccea4b17-1b05-4b02-957a-3ef868f86ec2","resolution":{"observed_at":"2026-08-11T16:47:59.670961Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.08842","last_updated":"2023-06-28T22:24:33Z","snapshot_observed_at":"2026-08-20T00:07:55.511322Z","submitted_at":"2023-06-15T04:06:24Z","title":"ViP: A Differentially Private Foundation Model for Computer Vision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.08842","snapshot_observed_at":"2026-08-11T16:47:59.099339Z","title":"Vip: A differentially private foundation model for com- puter vision,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.099339Z"},"links":{"cited_paper":"/paper/2306.08842","citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:cbd4a3d4f88505e0088385130c4e2390ef9893a042a9f2065d7a19f697ab8edc","observation_id":"840ab18a-2696-4241-bfa9-f3460a51885a","resolution":{"observed_at":"2026-08-11T16:47:59.099339Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:47:59.644315Z","title":"Perception prioritized training of diffusion models,","venue":null,"work_id":"0e768160-1e89-49b7-962a-5c142423c877","year":2022},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.103652Z"},"links":{"citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:22976f892e9347c0aec93b2a83de9d84c979af937d0f88d648d26d63c4cb4f07","observation_id":"a044a4e4-55ae-4f92-aa82-42b81c30c069","resolution":{"observed_at":"2026-08-11T16:47:59.652528Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:47:59.612942Z","title":"Fair sam- pling in diffusion models through switching mechanism,","venue":null,"work_id":"5d4df381-7b90-44e7-946c-8098d3238187","year":2024},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.108023Z"},"links":{"citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:4af0b4820f6357bd02a782321c0de848df34266ee3d190082ab1405a3e345a84","observation_id":"902135dd-0eeb-45f5-817c-5ad1ea4ba9d7","resolution":{"observed_at":"2026-08-11T16:47:59.621102Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T16:47:59.112687Z","title":"Denoising diffusion probabilistic models,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.112687Z"},"links":{"citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:3c3e64008c42286253aba3edb7148a29e93704b94e1d6d1e8861883ae01f52ea","observation_id":"657fdd14-bdd5-44c5-9f1a-d6576c736203","resolution":{"observed_at":"2026-08-11T16:47:59.112687Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:47:59.581033Z","title":"Varia- tional diffusion models,","venue":null,"work_id":"fa413cbf-3d2f-4216-8622-3dabab1aa408","year":2021},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.117681Z"},"links":{"citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:4102ae3c7bd43a360cf7da9c8ee2f2a9dab3828b6cd35d5512b92ddd05378d8b","observation_id":"6a967e0f-3ffb-4892-aa1a-919ba59ea9e1","resolution":{"observed_at":"2026-08-11T16:47:59.586396Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:47:59.561770Z","title":"Elucidating the design space of diffusion-based generative mod- els,","venue":null,"work_id":"5417a299-187d-4409-ba50-573f88dadce7","year":2022},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.122525Z"},"links":{"citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:f48af10e29959c588a4c0d431cc1d242de8ab934b0a3e83acac1ea150f978b62","observation_id":"8902e09f-de7c-462e-a359-bec38c378a8a","resolution":{"observed_at":"2026-08-11T16:47:59.566719Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:47:59.539181Z","title":"Efficient diffusion training via min-snr weighting strategy,","venue":null,"work_id":"c9da1694-9d8b-4f7e-aa6c-d70c9a7253a3","year":2023},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.126932Z"},"links":{"citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:2c7c6ad41d853c81b190fad564494c9d1ec3c9f66a2a1cf4599c0ed3fd40b8d5","observation_id":"e161fe6b-2319-460b-aa66-da6f3ed43504","resolution":{"observed_at":"2026-08-11T16:47:59.546234Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T16:47:59.131572Z","title":"Deep learning with differential privacy,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.131572Z"},"links":{"citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:6fee10dd1cc54b9a727619dce17d738e165f5a12b0d312a17e6881fb2c484ff0","observation_id":"56c106d0-9196-4b62-8ac5-2dc89410c5b2","resolution":{"observed_at":"2026-08-11T16:47:59.131572Z","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":"2026-08-11T16:47:59.136060Z","title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.136060Z"},"links":{"citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:01f62b28bb4c34a8fa1f57fa66e56459c989edb00ff77f03ca54180e5c5140e6","observation_id":"c569bf3e-4431-403c-b0c7-7a3efba7b15a","resolution":{"observed_at":"2026-08-11T16:47:59.136060Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:47:59.487964Z","title":"Classification accuracy score for conditional generative models,","venue":null,"work_id":"77b2d1fb-e3b2-4ce6-9601-7e7c3fd8103b","year":2019},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.140521Z"},"links":{"citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:4cdbc7d7cb97ed676c5b6029eccb3ab81ab2362916fe6fe91079dadf110bed20","observation_id":"d98bb825-a0b6-44a9-8e17-73162b587922","resolution":{"observed_at":"2026-08-11T16:47:59.493517Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02502","last_updated":"2022-10-05T20:19:21Z","snapshot_observed_at":"2026-08-11T15:38:14.931716Z","submitted_at":"2020-10-06T06:15:51Z","title":"Denoising Diffusion Implicit Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.02502","snapshot_observed_at":"2026-08-11T16:47:59.144837Z","title":"Denoising diffu- sion implicit models,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.144837Z"},"links":{"cited_paper":"/paper/2010.02502","citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:8441d830012217b0f582a2ef695efb23b4aa07b9d5f50f370e940ba8ab2f3dcb","observation_id":"2f83ef7f-f34c-47c7-b57e-4240606681fd","resolution":{"observed_at":"2026-08-11T16:47:59.144837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-19T03:28:59.817992Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-11T16:47:59.149451Z","title":"Opacus: User-friendly differential privacy library in pytorch,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.149451Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:17cfa13281ddfb8cfd46224dd2e3bcf8bcf12ccd8f3fa0ad54dcc3a477c396c7","observation_id":"70466643-d72f-4f5c-bcdb-08d80930971e","resolution":{"observed_at":"2026-08-11T16:47:59.149451Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.04590","last_updated":"2022-03-08T18:15:04Z","snapshot_observed_at":"2026-08-16T18:18:39.073166Z","submitted_at":"2021-06-08T18:00:01Z","title":"PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning","version":2},"cited_work":{"arxiv_id":"2106.04590","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.04590","snapshot_observed_at":"2026-08-11T16:47:59.255400Z","title":"PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning","venue":"cs.LG","work_id":"d10db463-73e6-45fe-b0ba-ee5f3e822ed8","year":2021},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.154503Z"},"links":{"cited_paper":"/paper/2106.04590","citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:e202bead561f10f25b24a878c712ee8b3c423cfbceadaaf13830f356b62b3213","observation_id":"9a5388be-f525-43da-8c1d-a08a5c48b764","resolution":{"observed_at":"2026-08-11T16:47:59.262388Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.02936","last_updated":"2023-10-05T04:47:52Z","snapshot_observed_at":"2026-08-20T00:07:32.352040Z","submitted_at":"2023-02-06T17:11:09Z","title":"Private GANs, Revisited","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.02936","snapshot_observed_at":"2026-08-11T16:47:59.159600Z","title":"Private gans, revis- ited,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.159600Z"},"links":{"cited_paper":"/paper/2302.02936","citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:db4ec6ea436719e68d48e84a394e83aa4b3474aadc2484bb318acee55ddd1fa7","observation_id":"8c20be3a-94de-4cd6-b16a-ba6741e636c1","resolution":{"observed_at":"2026-08-11T16:47:59.159600Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:47:59.472467Z","title":"Hermite polynomial features for private data generation,","venue":null,"work_id":"b743e711-e460-4fdb-8784-31409fb6c326","year":2022},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.164795Z"},"links":{"citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:296c255ea47c85165e976d232028361c2d6d999faf7197655bd9f482a288c269","observation_id":"1cd10b9d-da36-46ea-9662-486a8296a24a","resolution":{"observed_at":"2026-08-11T16:47:59.477741Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:47:59.455450Z","title":"Don’t generate me: Training differentially private generative models with sinkhorn divergence,","venue":null,"work_id":"d70bf055-3be1-4113-b68a-28b448c1c332","year":2021},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.169433Z"},"links":{"citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:b037820d4e1189793a9954b1563d3f6be5e0e6d5197b0d8aabba936a176e7a57","observation_id":"75b45e9e-12d8-4d17-b009-c201840daddb","resolution":{"observed_at":"2026-08-11T16:47:59.460869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:47:59.428638Z","title":"Scalable differentially private data generation via private aggregation of teacher ensembles,","venue":null,"work_id":"d1764758-607b-4e7b-a440-ee686fcaf60e","year":2019},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.174316Z"},"links":{"citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:5078417e7e06534902da49e8e5ec2e562b5c05e8239d7f173bb22fe46eae9643","observation_id":"83de240d-4b63-41e0-b61b-51fffddc1ab8","resolution":{"observed_at":"2026-08-11T16:47:59.435226Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:47:59.409835Z","title":"Dp- cgan: Differentially private synthetic data and label gen- eration,","venue":null,"work_id":"ac340aaa-06be-4e58-8f73-38f52d1bee89","year":2019},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.179055Z"},"links":{"citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:2b6e9d2d6522766c938ed330ad7bb8ce4031126fd3892b1581f4c95f04d61f21","observation_id":"4582e476-6468-4d15-9695-3a304a9b9dae","resolution":{"observed_at":"2026-08-11T16:47:59.414942Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:47:59.391494Z","title":"Datalens: Scalable privacy preserving training via gradient compression and aggregation,","venue":null,"work_id":"a9471487-0aa9-4dec-bcce-6ebcd3576fee","year":2021},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.183688Z"},"links":{"citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:c7c5646a70c7e12e093bff875db9405f3eaf075aace5502c16f52c6e80201476","observation_id":"82c06007-5c3a-478d-98c5-207e9f7a2dfa","resolution":{"observed_at":"2026-08-11T16:47:59.396367Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:47:59.374459Z","title":"Dp-merf: Differentially private mean embeddings with randomfea- tures for practical privacy-preserving data generation,","venue":null,"work_id":"c1e4bd33-255d-47eb-a440-5197bb9acfa4","year":2021},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.188221Z"},"links":{"citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:b9cd20194d879507aea5787764c60fc94978ee4ff8bee4c628277665aefe96f4","observation_id":"b6ad9f0c-e958-481c-9034-73ba30e67661","resolution":{"observed_at":"2026-08-11T16:47:59.380746Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:47:59.358381Z","title":"Dpgen: Differentially private generative energy- guided network for natural image synthesis,","venue":null,"work_id":"6933414e-4478-4733-96c9-30c8d28d9bf7","year":2022},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.192621Z"},"links":{"citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:1118d972ed02756592968a13a7a8c46162218be07ac291fb5888fb89108d434b","observation_id":"469f1977-98aa-4ddd-a31a-fc1bbb11bc0f","resolution":{"observed_at":"2026-08-11T16:47:59.363962Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:47:59.341701Z","title":"Dead leaves models: from space tessellation to random functions,","venue":null,"work_id":"aa87e418-4fb3-4ff1-9f51-80473942eb23","year":1997},"citing_paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T16:47:59.197683Z"},"links":{"citing_paper":"/paper/2412.09842"},"observation_digest":"sha256:07f6b820dc80cdc6d78c6de06c15a6d7038e5a1eac3511a92778b0faaa0c5393","observation_id":"b41ba32a-14b8-48de-b60f-3e67fbdae2ba","resolution":{"observed_at":"2026-08-11T16:47:59.347218Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.09842","last_updated":"2024-12-13T04:22:23Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-20T00:07:46.753714Z","submitted_at":"2024-12-13T04:22:23Z","title":"Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training"},"reference_resolution":{"displayed":29,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":1,"verified_fuzzy":20},"total_outbound_references":29},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 0 inbound Pith citation observations for arXiv:2412.09842."}