{"as_of":"2026-08-10T22:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5473c8e0daa61df2c5a4774c82bc3c74096f5f43df260d8f906ba0a54974f1a9","coverage":[{"denominator":43,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":43,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:37:08.228433Z","state":"measured"},{"denominator":46,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":46,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-14T10:52:33.767274Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-17T04:59:04.172920Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"cited_work":{"arxiv_id":"2505.24267","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.24267","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","venue":null,"work_id":"1bdec6ff-137a-41e0-bd18-66c01ac3cf86","year":2025},"citing_paper":{"arxiv_id":"2511.21600","last_updated":"2026-05-09T16:54:40Z","snapshot_observed_at":"2026-08-10T10:36:30.629875Z","submitted_at":"2025-11-26T17:16:14Z","title":"Robust Spectral Watermark for Synthetic Tabular Data","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-17T04:55:11.101649Z"},"links":{"cited_paper":"/paper/2505.24267","citing_paper":"/paper/2511.21600"},"observation_digest":"sha256:5fed61468f3c4f29c2ce5ec6c878b48eef8c6caf775549c63c305d7b06c4bed4","observation_id":"1986fb6b-31c5-4c11-8ef6-4059972c7137","resolution":{"observed_at":"2026-05-17T04:59:04.175565Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.24267","snapshot_observed_at":"2026-07-13T01:06:27.868238Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.09000","last_updated":"2026-07-10T00:06:42Z","snapshot_observed_at":"2026-07-15T23:17:59.590355Z","submitted_at":"2026-07-10T00:06:42Z","title":"RaMark: Radioactive Watermarking for Generated Tabular Data","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-13T01:06:27.868238Z"},"links":{"cited_paper":"/paper/2505.24267","citing_paper":"/paper/2607.09000"},"observation_digest":"sha256:77633b8f2e9451a4e15c52c419bc93373b70e01d8813540d3e60385c5288cea5","observation_id":"6b6fc8a4-ad7f-43a3-b0e3-774565e7f6b6","resolution":{"observed_at":"2026-07-13T01:06:27.868238Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.24267","snapshot_observed_at":"2026-07-14T10:52:33.767274Z","title":"MUSE: Model-agnostic tabular watermarking via multi-sample selection","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.10554","last_updated":"2026-07-12T04:03:55Z","snapshot_observed_at":"2026-08-10T16:24:48.864948Z","submitted_at":"2026-07-12T04:03:55Z","title":"Observation-Level Watermarking and Detection for Tabular Data","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-14T10:52:33.767274Z"},"links":{"cited_paper":"/paper/2505.24267","citing_paper":"/paper/2607.10554"},"observation_digest":"sha256:db08f60df0205c30a9ef1c1dfc63b382a607422e96b84ccbc277fdba77c8e110","observation_id":"7110302c-d3ed-4bce-b718-9b3800434af4","resolution":{"observed_at":"2026-07-14T10:52:33.767274Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2505.24267/citation-record","integrity":"/paper/2505.24267/integrity","json":"/paper/2505.24267/citation-record.json","paper":"/paper/2505.24267"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:12.086873Z","title":"Watermarking gpt outputs","venue":null,"work_id":"8589d737-0dab-42ec-8478-8b0b17acc5d4","year":2022},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:04.595839Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:854b65ac3bb124b2b01fd488d7560fbdfeced1c8e5be33deb276d08145286416","observation_id":"6a8d0ac2-f0d6-433b-a44a-ca59e634edd2","resolution":{"observed_at":"2026-08-07T12:37:12.213400Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T12:37:11.880284Z","title":"Generating synthetic data in finance: opportunities, challenges and pitfalls","venue":null,"work_id":"50f8d159-b405-4285-97bb-d92297263fcf","year":2020},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:04.660074Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:a6b02b37c5b848ebcc3bf545fcce85e547bd09067a5d657614b341d4ff754bbc","observation_id":"40d7ddb0-945c-4e59-b281-cbbe8b83a7b5","resolution":{"observed_at":"2026-08-07T12:37:11.995115Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.15127","last_updated":"2023-11-25T22:28:38Z","snapshot_observed_at":"2026-08-07T21:47:08.589400Z","submitted_at":"2023-11-25T22:28:38Z","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.15127","snapshot_observed_at":"2026-08-07T12:37:04.776426Z","title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:04.776426Z"},"links":{"cited_paper":"/paper/2311.15127","citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:2bd247e38b10156fff87a7d428cd874899d5aa5727f47faa8350ea5adcb64a38","observation_id":"eaaec39b-1b71-4bfd-abc2-1d3a0b864fec","resolution":{"observed_at":"2026-08-07T12:37:04.776426Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.08030","last_updated":"2021-01-20T08:58:29Z","snapshot_observed_at":"2026-08-10T08:06:00.751852Z","submitted_at":"2021-01-20T08:58:29Z","title":"Adversarial Attacks for Tabular Data: Application to Fraud Detection and Imbalanced Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.08030","snapshot_observed_at":"2026-08-07T12:37:04.893327Z","title":"Adversarial attacks for tabular data: Application to fraud detection and imbalanced data","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:04.893327Z"},"links":{"cited_paper":"/paper/2101.08030","citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:51a9b0f2fda606620702f54095e649b7c6b79c1cdfb4385edb0616b04de9fb06","observation_id":"56346855-ecb4-4a9a-a2ad-ef942cfac08e","resolution":{"observed_at":"2026-08-07T12:37:04.893327Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.10430","last_updated":"2023-07-19T19:40:21Z","snapshot_observed_at":"2026-08-10T06:07:58.441704Z","submitted_at":"2023-07-19T19:40:21Z","title":"DP-TBART: A Transformer-based Autoregressive Model for Differentially Private Tabular Data Generation","version":1},"cited_work":{"arxiv_id":"2307.10430","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.10430","snapshot_observed_at":"2026-08-07T12:37:08.482760Z","title":"DP-TBART: A Transformer-based Autoregressive Model for Differentially Private Tabular Data Generation","venue":"cs.LG","work_id":"47962cba-b926-4294-a56e-a5c0bb52b99c","year":2023},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:04.962943Z"},"links":{"cited_paper":"/paper/2307.10430","citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:1972a8f44eebd4d54a817e1f90c6b116cf64017224dad27894e2a18758f2cf3c","observation_id":"f49b3a0b-f474-454f-9541-1b8187c86176","resolution":{"observed_at":"2026-08-07T12:37:08.559259Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T12:37:11.646685Z","title":"Undetectable watermarks for language models","venue":null,"work_id":"456bb5bc-1c05-4c9a-9c2f-6c9ea34794e8","year":2024},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:05.053428Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:3ccb12df4862c18fdf294a5fdbe02984f51b283586e162eed6a230b2caa7f1c8","observation_id":"dfba2650-4699-4a91-9b99-78d94233b6ac","resolution":{"observed_at":"2026-08-07T12:37:11.745836Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T12:37:05.119536Z","title":"Scalable watermarking for identifying large language model outputs","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:05.119536Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:3cdf67e8b44528dcca67a28c2c1ab5fe449b503ef996b994ee5c567f98bc8929","observation_id":"80d996e6-a9a8-41fd-86e4-543057ffe12a","resolution":{"observed_at":"2026-08-07T12:37:05.119536Z","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":"2026-08-07T12:37:05.229820Z","title":"Diffusion models beat gans on image synthesis","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:05.229820Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:c822a0bfee0a7e8cf31767c22ecc1c584c5517dcc54e7c5da976b20a19318fb6","observation_id":"427063ac-5302-4328-8afc-06d2a6c91bb9","resolution":{"observed_at":"2026-08-07T12:37:05.229820Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.16414","last_updated":"2025-02-23T02:51:58Z","snapshot_observed_at":"2026-08-07T17:55:47.070204Z","submitted_at":"2025-02-23T02:51:58Z","title":"TabGen-ICL: Residual-Aware In-Context Example Selection for Tabular Data Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.16414","snapshot_observed_at":"2026-08-07T12:37:05.316171Z","title":"Tabgen-icl: Residual-aware in-context example selection for tabular data generation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:05.316171Z"},"links":{"cited_paper":"/paper/2502.16414","citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:a130a3cb1a4f2ea205015c5f442f4d988aeeaea400217346016046f72b19a849","observation_id":"dc20794f-37a4-43b4-b130-a9930b6edad5","resolution":{"observed_at":"2026-08-07T12:37:05.316171Z","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":"2026-08-07T12:37:11.457626Z","title":"Tabular and latent space synthetic data generation: a literature review","venue":null,"work_id":"d8a96b3f-d0d3-4791-9451-b70cce888c89","year":2023},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:05.401603Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:868926fe08e03311f5080e4b8686d69b166dff1bcf99ee42d3f3a43e35e4dd11","observation_id":"6db858a7-8566-4351-b290-8c66c5f6548e","resolution":{"observed_at":"2026-08-07T12:37:11.543832Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.04808","last_updated":"2024-10-18T07:05:57Z","snapshot_observed_at":"2026-08-10T06:07:34.388625Z","submitted_at":"2024-03-06T10:55:30Z","title":"WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.04808","snapshot_observed_at":"2026-08-07T12:37:05.470651Z","title":"Watermax: breaking the llm watermark detectability-robustness-quality trade-off","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:05.470651Z"},"links":{"cited_paper":"/paper/2403.04808","citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:ea3025ace0db4f71f45500c544315d6ef8472ad3ec87831d2c7f459e6267755e","observation_id":"86901e7c-080f-423e-9758-408d28bb6b04","resolution":{"observed_at":"2026-08-07T12:37:05.470651Z","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":"2026-08-07T12:37:11.241245Z","title":"Tabmt: Generating tabular data with masked transformers","venue":null,"work_id":"c928c31e-efd4-4de0-b584-7743a0fc5dc8","year":2024},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:05.548830Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:dbb1e3371db9da4537964e944b75b9781421f2016cf37b57e5109867e18b9b61","observation_id":"f98fdb23-9e4e-46ce-ba94-2b67520b2f48","resolution":{"observed_at":"2026-08-07T12:37:11.358782Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.14018","last_updated":"2024-05-22T21:52:12Z","snapshot_observed_at":"2026-07-06T18:18:12.096996Z","submitted_at":"2024-05-22T21:52:12Z","title":"Watermarking Generative Tabular Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.14018","snapshot_observed_at":"2026-08-07T12:37:05.637772Z","title":"Watermarking generative tabular data","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:05.637772Z"},"links":{"cited_paper":"/paper/2405.14018","citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:7fc407414cf27fc37889ae4ecfb63ff3bd34c7a92f2d0ebe04fe9e92bc48314e","observation_id":"fff91234-3e47-4149-a72b-017a6bf0f55b","resolution":{"observed_at":"2026-08-07T12:37:05.637772Z","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":"2026-08-07T12:37:10.968803Z","title":"Synthetic data generation for tabular health records: A systematic review","venue":null,"work_id":"54b62083-9346-43ca-8bc2-10f93c26ad2e","year":2022},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:05.758588Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:bafa241aa29b7e593176de6ad5b4daa58e0f55010de77700dc699c406b647b77","observation_id":"33c95dc4-b0ba-49d3-a4a6-8da379db185f","resolution":{"observed_at":"2026-08-07T12:37:11.102146Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T12:37:10.782420Z","title":"On exact inversion of dpm-solvers","venue":null,"work_id":"c6d60dc1-7cfd-4476-8117-206550320b6f","year":2024},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:05.843595Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:cf7e319b3eefbb8b3e2a08b32ad2f9f927a1179185d98b2ee22f386dd6de1052","observation_id":"25639e77-0652-48bb-a359-73f2ae13bbe5","resolution":{"observed_at":"2026-08-07T12:37:10.842732Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.10669","last_updated":"2023-10-18T02:02:08Z","snapshot_observed_at":"2026-08-08T13:36:08.291509Z","submitted_at":"2023-09-22T12:46:38Z","title":"Unbiased Watermark for Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.10669","snapshot_observed_at":"2026-08-07T12:37:06.024066Z","title":"Unbiased watermark for large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:06.024066Z"},"links":{"cited_paper":"/paper/2310.10669","citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:39b54453d3e1dd34136171dd3f813a6275c5ef4cb2732cd6a7df1fb18ab6ecb6","observation_id":"64ee12ce-08a9-4fdf-acc2-7c1fa312ecf0","resolution":{"observed_at":"2026-08-07T12:37:06.024066Z","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":"2026-08-07T12:37:10.646667Z","title":"Robin: Robust and invisible watermarks for diffusion models with adversarial optimization","venue":null,"work_id":"94e2a0d1-0188-4420-8474-98844d3412c1","year":2024},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:06.102851Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:1922afe26138b9db553f46732366232e93cd26c4ecfd7b2147d7b7b7de282974","observation_id":"55d016a7-aeb6-49cc-bde4-095892b0a4db","resolution":{"observed_at":"2026-08-07T12:37:10.709598Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T12:37:06.194161Z","title":"Elucidating the design space of diffusion-based generative models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:06.194161Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:6cbd6e533ed2005c39aba0ec4006077805066f13037632ab7bd4c2e987832652","observation_id":"58322704-f601-48b8-b026-9df4ee4a8899","resolution":{"observed_at":"2026-08-07T12:37:06.194161Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6114","last_updated":"2022-12-10T21:04:00Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2013-12-20T20:58:10Z","title":"Auto-Encoding Variational Bayes","version":11},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6114","snapshot_observed_at":"2026-08-07T12:37:06.287193Z","title":"Auto-encoding variational bayes","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:06.287193Z"},"links":{"cited_paper":"/paper/1312.6114","citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:9dc707541422a940d5d4bb871ec72822b20e85ddad05617320d10511a259fa0d","observation_id":"adf7246f-4675-4b7f-ae5d-8af0c728075c","resolution":{"observed_at":"2026-08-07T12:37:06.287193Z","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":"2026-08-07T12:37:06.381490Z","title":"A watermark for large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:06.381490Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:56939fdbec30126afbfcabdefd82d4cba1b5fb2a4828313ded71cb62277cd518","observation_id":"c20f9b32-958f-49f3-a7da-d992c05ad967","resolution":{"observed_at":"2026-08-07T12:37:06.381490Z","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":"2026-08-07T12:37:06.501494Z","title":"Tabddpm: Modelling tabular data with diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:06.501494Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:9e699f7b1ed76c4b14bdb40081dc412b6aef6378df24681af97881bb34162aee","observation_id":"3bcbd947-9678-4be9-9ed8-ac968ed95185","resolution":{"observed_at":"2026-08-07T12:37:06.501494Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.15593","last_updated":"2024-06-06T04:53:25Z","snapshot_observed_at":"2026-07-06T15:59:52.247013Z","submitted_at":"2023-07-28T14:52:08Z","title":"Robust Distortion-free Watermarks for Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.15593","snapshot_observed_at":"2026-08-07T12:37:06.595951Z","title":"Robust distortion-free watermarks for language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:06.595951Z"},"links":{"cited_paper":"/paper/2307.15593","citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:9803f6e961f4a820ad4f5263bef31a465d7a7884ec6962e33a162393c1405d2b","observation_id":"3e531a87-2fc6-42d6-9267-dcea0ee856cd","resolution":{"observed_at":"2026-08-07T12:37:06.595951Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06356","last_updated":"2024-05-19T12:24:40Z","snapshot_observed_at":"2026-08-10T22:33:45.063331Z","submitted_at":"2023-10-10T06:49:43Z","title":"A Semantic Invariant Robust Watermark for Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06356","snapshot_observed_at":"2026-08-07T12:37:06.661668Z","title":"A semantic invariant robust watermark for large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:06.661668Z"},"links":{"cited_paper":"/paper/2310.06356","citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:bf5835d8c1bb96bd6b7355750f31368054786f62d2706bc7674b0e0f99f59592","observation_id":"c7158a0a-cddb-41e5-b7f4-645b683b0dd5","resolution":{"observed_at":"2026-08-07T12:37:06.661668Z","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":"2026-08-07T12:37:10.421447Z","title":"A survey of text watermarking in the era of large language models","venue":null,"work_id":"73d40c67-b5e5-4033-8e0d-aaf751263607","year":2024},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:06.724995Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:3b317343894d080c19580f4eb2677cf17bf60df0bf436c86b7e37d737c16bfb5","observation_id":"3c4a6230-519d-4c95-9546-f3c01fcd00a7","resolution":{"observed_at":"2026-08-07T12:37:10.532924Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T12:37:10.201660Z","title":"Tabular transformers for modeling multivariate time series","venue":null,"work_id":"8fd1a0fd-cf7d-4fd5-8f44-ae2e63fdd653","year":2021},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:06.803133Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:3277f34e7afe4e35238f4f1002f8f06f2e1083b3397e36e76cb91cde92731b17","observation_id":"b5c62511-7dbc-47e7-a30c-2a50c49c8abe","resolution":{"observed_at":"2026-08-07T12:37:10.325057Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.10051","last_updated":"2024-10-26T05:11:11Z","snapshot_observed_at":"2026-08-10T22:33:49.229306Z","submitted_at":"2024-05-16T12:40:01Z","title":"MarkLLM: An Open-Source Toolkit for LLM Watermarking","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.10051","snapshot_observed_at":"2026-08-07T12:37:06.875230Z","title":"Markllm: An open-source toolkit for llm watermarking","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:06.875230Z"},"links":{"cited_paper":"/paper/2405.10051","citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:4f85de991095c5221f562bc5e1f8ab2266b308aabedc979eb1bcf24e022f5aff","observation_id":"666907ae-5311-4209-a003-01c18dfea5c3","resolution":{"observed_at":"2026-08-07T12:37:06.875230Z","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":"2026-08-07T12:37:10.007720Z","title":"Effective real image editing with accelerated iterative diffusion inversion","venue":null,"work_id":"3433e935-9025-40be-97cb-fc1ce7f81f13","year":2023},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:06.955385Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:82e6f0bc85309281222d884d78f3ad0177d21170d0442fe94146b9544f22ddcf","observation_id":"2dd49ba3-e9d9-48c1-9831-152ab49e8f92","resolution":{"observed_at":"2026-08-07T12:37:10.084005Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T12:37:07.036367Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:07.036367Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:17a7d0abd9320a9196eb9c23b13bba874f7d6c4ccd7b89243cbfc745120ef20d","observation_id":"14c3518d-6fe6-4ecd-a5c6-1028a556517a","resolution":{"observed_at":"2026-08-07T12:37:07.036367Z","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":"2026-08-07T12:37:09.836940Z","title":"Tabdiff: a unified diffusion model for multi-modal tabular data generation","venue":null,"work_id":"efc97fc1-870f-4768-ab2b-a0ad1c8a90da","year":2024},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:07.099629Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:d2988dac2e1783d0e7be6499c5d4bb75ba19838c702435a6d0db50a2cd87d2d5","observation_id":"d8378d43-7b27-4996-b928-bcf3bc651a25","resolution":{"observed_at":"2026-08-07T12:37:09.939920Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02502","last_updated":"2022-10-05T20:19:21Z","snapshot_observed_at":"2026-07-06T10:01:50.133383Z","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":"2026-08-07T12:37:07.185368Z","title":"Denoising diffusion implicit models","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:07.185368Z"},"links":{"cited_paper":"/paper/2010.02502","citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:85b7826b4cefd2e8277c06ad19a28759b085d903f80bf30fb3e651708401d426","observation_id":"acd4f040-8585-405d-aa94-a72a03a0a22d","resolution":{"observed_at":"2026-08-07T12:37:07.185368Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.20030","last_updated":"2023-07-04T03:52:06Z","snapshot_observed_at":"2026-08-04T13:34:47.513256Z","submitted_at":"2023-05-31T17:00:31Z","title":"Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.20030","snapshot_observed_at":"2026-08-07T12:37:07.278256Z","title":"Tree-ring watermarks: Fingerprints for diffusion images that are invisible and robust","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:07.278256Z"},"links":{"cited_paper":"/paper/2305.20030","citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:5c7723c3381a8d05173e2a2d9e038bdf7d016909a62549abf4d10cdd363a685f","observation_id":"e62ecb67-a06a-4a29-b6cc-5e735f60956c","resolution":{"observed_at":"2026-08-07T12:37:07.278256Z","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":"2026-08-07T12:37:09.623470Z","title":"Quantile normalization -- Wikipedia , the free encyclopedia","venue":null,"work_id":"ca9e63c5-d9a8-4352-81b8-7fe5b9c9e2b9","year":2025},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:07.364040Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:3a7d2b49e8bbaac30707cdfacf64213173a16ee9d1f841042efdf386d7f39310","observation_id":"520c6eea-0067-407c-b7b6-0ed60dffc95d","resolution":{"observed_at":"2026-08-07T12:37:09.733369Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T12:37:09.409337Z","title":"A survey on llm-generated text detection: Necessity, methods, and future directions","venue":null,"work_id":"cab6c0e8-371f-4b2e-9637-8ec71a40ce08","year":2025},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:07.428835Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:c75807acf14cf11e5af3b86d35f872d3ad6969cc4607305855c249c02b83cfad","observation_id":"e006e488-9c95-4815-a379-f4e2a477414c","resolution":{"observed_at":"2026-08-07T12:37:09.512284Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T12:37:09.239900Z","title":"Gaussian shading: Provable performance-lossless image watermarking for diffusion models","venue":null,"work_id":"9233432e-fa3f-484d-8318-5dcd9b508ec8","year":2024},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:07.513975Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:7c7f6788ac28038fcafcf3478335d744b5b107c68d69728936b89e79ebbaf2fa","observation_id":"c8ba6adf-6722-4f69-a5e2-481e6e0d1ab6","resolution":{"observed_at":"2026-08-07T12:37:09.332290Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.21523","last_updated":"2024-10-28T20:49:26Z","snapshot_observed_at":"2026-08-04T02:00:25.290354Z","submitted_at":"2024-10-28T20:49:26Z","title":"Diffusion-nested Auto-Regressive Synthesis of Heterogeneous Tabular Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.21523","snapshot_observed_at":"2026-08-07T12:37:07.605554Z","title":"Diffusion-nested auto-regressive synthesis of heterogeneous tabular data","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:07.605554Z"},"links":{"cited_paper":"/paper/2410.21523","citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:5f7eb37c78bb4bb3fc347de1694eecab4df05803ae98839bdea1abe229ee95c4","observation_id":"d2df0b1b-d5b2-4b59-be46-83297c6246e6","resolution":{"observed_at":"2026-08-07T12:37:07.605554Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.20690","last_updated":"2025-05-24T02:59:32Z","snapshot_observed_at":"2026-07-06T18:23:10.807498Z","submitted_at":"2024-05-31T08:35:56Z","title":"DiffPuter: Empowering Diffusion Models for Missing Data Imputation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.20690","snapshot_observed_at":"2026-08-07T12:37:07.673255Z","title":"Unleashing the potential of diffusion models for incomplete data imputation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:07.673255Z"},"links":{"cited_paper":"/paper/2405.20690","citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:fba142278b9cc85ca89eb5dea990b6c8afcdaf5ba2d88acb52436ec0298dba36","observation_id":"412aa208-7f17-478f-a272-5bf7af86086a","resolution":{"observed_at":"2026-08-07T12:37:07.673255Z","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":"2026-08-07T12:37:09.098319Z","title":"Mixed-type tabular data synthesis with score-based diffusion in latent space","venue":null,"work_id":"df872bf7-3603-44bf-8e5e-2e5a61f296c6","year":2024},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:07.747038Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:6c8b7b6c6e2dc6a07b1df5160f37aed8a9a18e265109fa47f4f671728eee8a17","observation_id":"c9177b8d-5776-44ec-b1d0-237d2fa9097e","resolution":{"observed_at":"2026-08-07T12:37:09.178687Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.17439","last_updated":"2023-10-13T04:50:04Z","snapshot_observed_at":"2026-08-07T18:16:43.461993Z","submitted_at":"2023-06-30T07:24:32Z","title":"Provable Robust Watermarking for AI-Generated Text","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.17439","snapshot_observed_at":"2026-08-07T12:37:07.806777Z","title":"Provable robust watermarking for ai-generated text","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:07.806777Z"},"links":{"cited_paper":"/paper/2306.17439","citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:e6fea5ebdcbe9c37b49ffbfbe0d039c9cafeb9b74fc0aa270bc429ea8157b5a3","observation_id":"8ec1d7c5-9ee2-4b3e-a277-8e68879de188","resolution":{"observed_at":"2026-08-07T12:37:07.806777Z","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":"2026-08-07T12:37:08.836685Z","title":"Tabularmark: Watermarking tabular datasets for machine learning","venue":null,"work_id":"99e7c1df-a916-4a72-86bf-ec7b11b133d0","year":2024},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:07.879673Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:71d24da13821d755685ee910044bb34051429d69ad91f4d55b826c5febac0500","observation_id":"2a005ff7-5a06-4111-ab01-90ebda3bcd8d","resolution":{"observed_at":"2026-08-07T12:37:08.961268Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T12:37:08.695680Z","title":"Galjaard, Pin-Yu Chen, Robert Birke, Cornelis Bos, and Lydia Y","venue":null,"work_id":"3a904985-f882-44ad-a4ee-58e835790b51","year":2025},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:07.952794Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:6c1c1facb07e00afad4169d652b2630423f50bd86d642058d60ba7825df76be7","observation_id":"40b8dac8-16e2-41c2-8096-6c4324b51acf","resolution":{"observed_at":"2026-08-07T12:37:08.756918Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T12:37:08.026741Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:08.026741Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:73fd16b21eea72e7f29637447169e9e0a8c4efbb8ddf960110698500519bdae4","observation_id":"1871ef3f-0f8c-40d2-a38e-5f1faa60111f","resolution":{"observed_at":"2026-08-07T12:37:08.026741Z","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":"2026-08-07T12:37:08.125376Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:08.125376Z"},"links":{"citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:78f81ef4b005519a23e46f2107146c60773766927f14b24f5f51c28572d5026c","observation_id":"0269e868-edda-48d6-b1b2-948ae0b22c79","resolution":{"observed_at":"2026-08-07T12:37:08.125376Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.14195","last_updated":"2025-02-25T11:54:25Z","snapshot_observed_at":"2026-08-10T19:53:47.834366Z","submitted_at":"2025-01-24T02:57:09Z","title":"VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.14195","snapshot_observed_at":"2026-08-07T12:37:08.228433Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-07T12:37:08.228433Z"},"links":{"cited_paper":"/paper/2501.14195","citing_paper":"/paper/2505.24267"},"observation_digest":"sha256:34f5898ed3224ca218b83fab63336a7317c074e3e57eac46dc88df40a9ba084d","observation_id":"06e69e1d-d8fd-444a-bc0e-b2b1cd7d28f1","resolution":{"observed_at":"2026-08-07T12:37:08.228433Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.24267","last_updated":"2025-05-30T06:45:31Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-10T06:07:44.859924Z","submitted_at":"2025-05-30T06:45:31Z","title":"MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection"},"reference_resolution":{"displayed":43,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":24,"verified_exact":1,"verified_fuzzy":18},"total_outbound_references":43},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 3 inbound Pith citation observations for arXiv:2505.24267."}