{"as_of":"2026-08-05T12:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:22b5757557e59e9815ea420c3d1a9d647cbe4585c5069c3a5a2d7708a283443c","coverage":[{"denominator":47,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":47,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T20:34:11.265532Z","state":"measured"},{"denominator":47,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":47,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-05T06:32:48.257954+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/2511.19316/citation-record","integrity":"/paper/2511.19316/integrity","json":"/paper/2511.19316/citation-record.json","paper":"/paper/2511.19316"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T20:34:07.182328Z","title":"Ntire 2017 challenge on single image super-resolution: Dataset and study","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:07.182328Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:e5d679e1a1b4d1782eaf57f699051382fc630758f8aa849c8b91bf2cc7b0872a","observation_id":"1f693154-8721-4ada-bbaa-c8a75c95e3aa","resolution":{"observed_at":"2026-08-03T20:34:07.182328Z","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":"2026-08-03T20:34:07.344010Z","title":"Variational image compres- sion with a scale hyperprior","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:07.344010Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:5f03c6a6023905e5020c8f8961f69cca8649e5555c02a76b43a4ad940c6be2a7","observation_id":"82136777-d399-4525-9e7b-e3a16a22ece7","resolution":{"observed_at":"2026-08-03T20:34:07.344010Z","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":"2026-08-03T20:34:07.484411Z","title":"Cold diffusion: Inverting arbitrary im- age transforms without noise.Advances in Neural Informa- tion Processing Systems, 36:41259–41282, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:07.484411Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:5a46e76ed040776715d36bbaf5c2e7654933a9d7a727661b9c3c447cbb40d25b","observation_id":"e8a6c4cb-04df-4dcc-8045-b04b54897aa5","resolution":{"observed_at":"2026-08-03T20:34:07.484411Z","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":"2026-08-03T20:34:07.583572Z","title":"Trustmark: Robust watermarking and watermark removal for arbitrary resolution images","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:07.583572Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:14e93a17b67fc6e5a401adb53583df53883fb5c18c573a0604d324deb729c281","observation_id":"6947d5d4-8673-4143-bd85-1ef93e3a39e4","resolution":{"observed_at":"2026-08-03T20:34:07.583572Z","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":"2026-08-03T20:34:07.678749Z","title":"Learned image compression with discretized gaussian mixture likelihoods and attention modules","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:07.678749Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:b29e79ba9d79ba864906c2de35b19e834e2d5274ee0e186664f98abe873d5ccf","observation_id":"9f9cea1a-3bc0-41c3-9749-101c580ee4b9","resolution":{"observed_at":"2026-08-03T20:34:07.678749Z","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":"2026-08-03T20:34:07.794162Z","title":"Digital watermarking.Journal of Electronic Imaging, 11(3):414–414, 2002","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:07.794162Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:152ea182bdc656e459c13af64e0a3a759fdf31328941ade183ce4204384b7d55","observation_id":"2e96f912-695c-4c72-864d-714d62a2a91d","resolution":{"observed_at":"2026-08-03T20:34:07.794162Z","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":"2026-08-03T20:34:07.867382Z","title":"Irnext: rethinking convolutional network design for image restoration","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:07.867382Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:750374430b3eb4f8ceac5fe75ccf4cc81019ef91f167268fe7043bd460e6d9a8","observation_id":"83d8f305-defe-45fe-8d6d-e5e8575722cc","resolution":{"observed_at":"2026-08-03T20:34:07.867382Z","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":"2026-08-03T20:34:08.005976Z","title":"Revitalizing convolutional network for image restoration","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:08.005976Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:42185b944b1a5e75c61f06304f459822fdb48c4efdcd3d0b664a41ebe08cc429","observation_id":"9d8d832d-2bd9-46c0-a8a0-737a6af8e2c3","resolution":{"observed_at":"2026-08-03T20:34:08.005976Z","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":"2026-08-03T20:34:08.118628Z","title":"Ft-shield: A watermark against unauthorized fine-tuning in text-to-image diffusion models.ACM SIGKDD Explorations Newsletter, 26(2):76–88, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:08.118628Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:6cb3ef6c5e7ae6842bfe00d220bf354716aaa9b90b3c56f6675b070cedfe84b1","observation_id":"e61eef6d-d0f6-434a-b607-b7611cf9d74f","resolution":{"observed_at":"2026-08-03T20:34:08.118628Z","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":"2026-08-03T20:34:08.274549Z","title":"Diffusionshield: A water- mark for data copyright protection against generative diffu- sion models.ACM SIGKDD Explorations Newsletter, 26(2): 60–75, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:08.274549Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:958c4b8ec32a38d9f71e298d72cc698bdd53cb50a4a06cca2b25cf93c4419870","observation_id":"acf329bc-f6e3-4212-b3aa-8428fbf79b47","resolution":{"observed_at":"2026-08-03T20:34:08.274549Z","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":"2026-08-03T20:34:08.392056Z","title":"Freecustom: Tuning- free customized image generation for multi-concept compo- sition","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:08.392056Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:10d701f67307f9fd84db99cd156716a7da96326aaf5fbdfdc0e5e8eb4841bbac","observation_id":"bf4badbb-c1b0-4756-839b-039108951a75","resolution":{"observed_at":"2026-08-03T20:34:08.392056Z","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":"2026-08-03T20:34:08.496298Z","title":"Are diffusion models vulnerable to membership inference attacks? InInternational Conference on Machine Learning, pages 8717–8730","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:08.496298Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:4fd4b34b4b114b378e752b282d8de59db6897f27fce11528e1bc02328a8a7b01","observation_id":"274e39d8-cb7b-4abc-9461-79d924e34024","resolution":{"observed_at":"2026-08-03T20:34:08.496298Z","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":"2026-08-03T20:34:08.565353Z","title":"Cdi: Copyrighted data identification in dif- fusion models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:08.565353Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:3eeab2ce10977af27e057a4c8831a946961a0a0072a1fb4e596f5d0a2422c75d","observation_id":"1e8cd4b6-d5a7-46b6-927b-85f6455c1b99","resolution":{"observed_at":"2026-08-03T20:34:08.565353Z","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":"2026-08-03T20:34:08.654563Z","title":"The stable signature: Rooting watermarks in latent diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:08.654563Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:d70d36903727b31f2caa260f104cc805699f8078fa85f88dd2405255ef36e6b9","observation_id":"a185890d-c2ad-47ef-9f75-5ed4c9ac8ab6","resolution":{"observed_at":"2026-08-03T20:34:08.654563Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.01618","last_updated":"2022-08-02T17:50:36Z","snapshot_observed_at":"2026-08-02T23:40:32.342515Z","submitted_at":"2022-08-02T17:50:36Z","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.01618","snapshot_observed_at":"2026-08-03T20:34:08.765105Z","title":"An image is worth one word: Personalizing text-to- image generation using textual inversion.arXiv preprint arXiv:2208.01618, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:08.765105Z"},"links":{"cited_paper":"/paper/2208.01618","citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:d3dc2949c41568670f0f4a59120bb2b19baae0e79c10084cee36a33d14a4cd18","observation_id":"3ebecb3b-0a0a-4131-91fb-592753895926","resolution":{"observed_at":"2026-08-03T20:34:08.765105Z","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":"2026-08-03T20:34:08.861795Z","title":"Svdiff: Compact param- eter space for diffusion fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:08.861795Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:f1f16a22b201d6c4f7864c0e173456ccb54df4a2ba3cd232330bedc0f5d95d2f","observation_id":"38adc59d-e3ad-47d8-ad63-fb6cb4df13d9","resolution":{"observed_at":"2026-08-03T20:34:08.861795Z","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":"2026-08-03T20:34:08.935828Z","title":"Gans trained by a two time-scale update rule converge to a local nash equilib- rium.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:08.935828Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:d96e31778baf96b1fbada6ce6be247d1ef40517ca8ce6ab04c2763844c2abaf1","observation_id":"84a38d06-2334-419c-b79e-bac53c1d9297","resolution":{"observed_at":"2026-08-03T20:34:08.935828Z","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":"2026-08-03T20:34:09.054111Z","title":"Lora: Low-rank adaptation of large language models.ICLR, 1(2):3, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:09.054111Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:ec93061bed0eda72bd7f2b2923320e3e7d13aaa02a4e6ba31bc5fbf66997c186","observation_id":"3fa43b86-4252-4930-b8d3-7ed2519c3751","resolution":{"observed_at":"2026-08-03T20:34:09.054111Z","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":"2026-08-03T20:34:09.165679Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:09.165679Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:9ebcfefa2e27bed52ba35d714581107bf88155100ae83c4462aa51b24f207850","observation_id":"4c27cd87-17a3-4840-a6c7-eff246d1bc33","resolution":{"observed_at":"2026-08-03T20:34:09.165679Z","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":"2026-08-03T20:34:09.268114Z","title":"Multi-concept customization of text-to-image diffusion","venue":null,"work_id":null,"year":1931},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:09.268114Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:476222824561c346a4ef9b319cf886c27a53f612585212a98661ba293bc4ac9d","observation_id":"b2bcbb2a-abf8-4aaf-95c7-572e3e206e84","resolution":{"observed_at":"2026-08-03T20:34:09.268114Z","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":"2026-08-03T20:34:09.347340Z","title":"Towards reli- able verification of unauthorized data usage in personalized text-to-image diffusion models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:09.347340Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:d73852f11c648104315dd1877778d1f059457e202642fb7edd4a39deb5e8d744","observation_id":"f49ef7e4-ee7e-4aba-b8c2-2255cdc3d340","resolution":{"observed_at":"2026-08-03T20:34:09.347340Z","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":"2026-08-03T20:34:09.413869Z","title":"Swinir: Image restoration us- ing swin transformer","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:09.413869Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:a73d6ea60004d2626c157edb4fcfce5f7b9f15415a6623f76f0847b36441faa3","observation_id":"cdae65b9-2ca6-4ec3-88d4-e71d9ee7cee6","resolution":{"observed_at":"2026-08-03T20:34:09.413869Z","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":"2026-08-03T20:34:09.463201Z","title":"Deep learning face attributes in the wild","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:09.463201Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:0ee7951e102dc6d6a3ae02aae026b75410a6217fb7151cf3cd4ef175a8f8fbe4","observation_id":"45ddf9bd-0025-45ee-8f35-a14af699255a","resolution":{"observed_at":"2026-08-03T20:34:09.463201Z","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":"2026-08-03T20:34:09.543199Z","title":"Waterloo ex- 9 ploration database: New challenges for image quality assess- ment models.IEEE Transactions on Image Processing, 26 (2):1004–1016, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:09.543199Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:af2305b61e5a1b825a4c570ee6e9b01c1806b7e2deccd772d67c5000acb2af84","observation_id":"f7cd27fb-3368-4ba3-8c4a-e50011c74fce","resolution":{"observed_at":"2026-08-03T20:34:09.543199Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.07754","last_updated":"2023-06-13T13:12:04Z","snapshot_observed_at":"2026-07-06T15:42:02.856661Z","submitted_at":"2023-06-13T13:12:04Z","title":"Generative Watermarking Against Unauthorized Subject-Driven Image Synthesis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.07754","snapshot_observed_at":"2026-08-03T20:34:09.632031Z","title":"Generative watermarking against unauthorized subject-driven image synthesis.arXiv preprint arXiv:2306.07754, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:09.632031Z"},"links":{"cited_paper":"/paper/2306.07754","citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:1702b1f9dec23b18acadfc9d0a505eec890b3f42bb0f0142cfd0853942f93167","observation_id":"9472c97e-8b98-425a-8c1c-ba981380eedd","resolution":{"observed_at":"2026-08-03T20:34:09.632031Z","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":"2026-08-03T20:34:09.703670Z","title":"Dwt-dct-svd based watermark- ing","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:09.703670Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:8c3d2f1599f7bb134b81ac33269ce94aa148ddf0b69ddb94de5ff46874781460","observation_id":"de13ecea-2cc1-4010-9606-44d9a13c611d","resolution":{"observed_at":"2026-08-03T20:34:09.703670Z","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":"2026-08-03T20:34:09.795818Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:09.795818Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:16dd717d6efaac8d128fb20fc6cdc4162b31bb3f91f222a5c06246379f6d967d","observation_id":"db8fe806-f98a-48b8-9c6e-f524959e1ca8","resolution":{"observed_at":"2026-08-03T20:34:09.795818Z","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":"2026-08-03T20:34:09.865902Z","title":"Entruth: Enhanc- ing the traceability of unauthorized dataset usage in text-to- image diffusion models with minimal and robust alterations","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:09.865902Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:2eb84ec8ed33cfb6d35b8dd0179bf3d0151b64023a9e487bc438093c64bfdeda","observation_id":"edd38128-6f2a-4827-8f9f-eb1549dab278","resolution":{"observed_at":"2026-08-03T20:34:09.865902Z","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":"2026-08-03T20:34:09.925480Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:09.925480Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:88bd267595c17674306de0a6fe56e5ded33f945e5a89c27b9c1d938aa3a69f07","observation_id":"3bcc969f-f3ee-4e30-a487-6c2aaae20143","resolution":{"observed_at":"2026-08-03T20:34:09.925480Z","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":"2026-08-03T20:34:10.010494Z","title":"Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:10.010494Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:350c331f4d0572ea56049af88a5887857db3a750c36f2dfc95f7d00867cf137c","observation_id":"fd60240c-8e97-4054-bd42-343c383004a5","resolution":{"observed_at":"2026-08-03T20:34:10.010494Z","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":"2026-08-03T20:34:10.072645Z","title":"Combinational image wa- termarking in the spatial and frequency domains.Pattern Recognition, 36(4):969–975, 2003","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:10.072645Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:c8556351a09ef2019836974e4f44be1541ce74c741bf6b49a89dcb221fc00342","observation_id":"b5e60b3a-4374-40d5-87ec-e1146a40237b","resolution":{"observed_at":"2026-08-03T20:34:10.072645Z","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":"2026-08-03T20:34:10.160768Z","title":"Deep unsupervised learning using nonequilibrium thermodynamics","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:10.160768Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:6d2370edd59294eac1d21bc6135548f01fc6a70ceceef2cd2dfd478cb80d14fd","observation_id":"d70bfb8b-6787-4bde-be99-c2513f76cb14","resolution":{"observed_at":"2026-08-03T20:34:10.160768Z","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":"2026-08-03T20:34:10.215011Z","title":"Improved techniques for training score-based generative models.Advances in neural information processing systems, 33:12438–12448, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:10.215011Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:9d8fc1830887219f466501f9e0c157a7f0965f60a2135e3beac8657e1c66d2c7","observation_id":"a2b240c5-636d-453f-848b-572f0f941502","resolution":{"observed_at":"2026-08-03T20:34:10.215011Z","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":"2026-08-03T20:34:10.266925Z","title":"Denet: Disen- tangled embedding network for visible watermark removal","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:10.266925Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:5fcf9e2e7364e83149873f6c10ff68a1cc92b2385ce8d9f4a644bcf3138ce9eb","observation_id":"12fc6c19-c33c-4626-8460-c2dbc52a5169","resolution":{"observed_at":"2026-08-03T20:34:10.266925Z","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":"2026-08-03T20:34:10.406146Z","title":"Stegastamp: Invisible hyperlinks in physical photographs","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:10.406146Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:a0803743d8e94137cfa2c92e42ee70b52f22dabda989d312a97ba80ec892b027","observation_id":"ed1e4365-abb0-44f2-b524-8b34aad31b1b","resolution":{"observed_at":"2026-08-03T20:34:10.406146Z","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":"2026-08-03T20:34:10.486646Z","title":"Ex- ploring clip for assessing the look and feel of images","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:10.486646Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:7ae617ec189d3ba7bee417892dd7da54f6b782ca8862d547f11086a804301cfb","observation_id":"4e490abd-b25f-4ec0-8789-2528e703ab61","resolution":{"observed_at":"2026-08-03T20:34:10.486646Z","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":"2026-08-03T20:34:10.525478Z","title":"Diagnosis: Detecting unau- thorized data usages in text-to-image diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:10.525478Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:39e078347fa05ea499c3ec045d3f4a14bad4a02fd63e7040b536e0338c0673f5","observation_id":"f609c102-8b15-47eb-8f3b-807dc4bdfbf1","resolution":{"observed_at":"2026-08-03T20:34:10.525478Z","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":"2026-08-03T20:34:10.620656Z","title":"Powerful and flexible: Personalized text- to-image generation via reinforcement learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:10.620656Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:9c7f286b2cea910888def744b0b15d52aaa4ba209754a39666b6341d8f9b11e3","observation_id":"04e9260c-0065-46c2-b979-68049d24a361","resolution":{"observed_at":"2026-08-03T20:34:10.620656Z","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":"2026-08-03T20:34:10.686475Z","title":"Tree-rings watermarks: Invisible fingerprints for diffusion images.Advances in Neural Information Process- ing Systems, 36:58047–58063, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:10.686475Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:d1c7021674901983046e932fa956469c4a25f0882a51e6a63e705042a95e0b0d","observation_id":"df1eec15-f925-4b89-a9a4-951674cc6563","resolution":{"observed_at":"2026-08-03T20:34:10.686475Z","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":"2026-08-03T20:34:10.745594Z","title":"High- capacity convolutional video steganography with temporal residual modeling","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:10.745594Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:dc68643db1c94de7a9f199355c13a06d9b5cf765df6cf1a7fc8ac924e663d4c6","observation_id":"142a940e-7a3d-41c9-b62d-dafc15d436da","resolution":{"observed_at":"2026-08-03T20:34:10.745594Z","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":"2026-08-03T20:34:10.832253Z","title":"Wikiart: Visual art encyclopedia.https://www","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:10.832253Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:ac68af9db2f2e9eb8747356f15430b4a9c0103e4868215d6b1e4f4f5ae9496ae","observation_id":"2ec4810b-73f8-4fba-b31f-abc5060eb23a","resolution":{"observed_at":"2026-08-03T20:34:10.832253Z","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":"2026-08-03T20:34:10.906092Z","title":"Artificial fingerprinting for generative models: Root- ing deepfake attribution in training data","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:10.906092Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:ca4f6b927b2f43ccbbc02e85c0f2e4de2c7b01f956a8461b172885c2d6f94bb5","observation_id":"e057bd88-baa2-46c6-b136-a3e0887cee9d","resolution":{"observed_at":"2026-08-03T20:34:10.906092Z","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":"2026-08-03T20:34:10.956711Z","title":"Invisible steganog- raphy via generative adversarial networks.Multimedia tools and applications, 78(7):8559–8575, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:10.956711Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:e9cf2f8e5da6e696e17cebcf05b6f0a2376dc08013550471a13139acd665a166","observation_id":"516010a4-4971-4176-adb5-ec0805cdf3d9","resolution":{"observed_at":"2026-08-03T20:34:10.956711Z","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":"2026-08-03T20:34:11.007795Z","title":"Invisible image watermarks are provably removable using generative ai.Advances in neural information processing systems, 37:8643–8672, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:11.007795Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:e633055ca322aaae13b5b229cf73bba24bd90f8ebb5cb4320749f43231cd3d8b","observation_id":"855984d7-9987-4400-b252-4603dbed79f2","resolution":{"observed_at":"2026-08-03T20:34:11.007795Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.10137","last_updated":"2023-10-15T10:04:38Z","snapshot_observed_at":"2026-07-06T15:05:00.197020Z","submitted_at":"2023-03-17T17:25:10Z","title":"A Recipe for Watermarking Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.10137","snapshot_observed_at":"2026-08-03T20:34:11.083384Z","title":"A recipe for watermarking dif- fusion models.arXiv preprint arXiv:2303.10137, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:11.083384Z"},"links":{"cited_paper":"/paper/2303.10137","citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:94b21db527609aef66ffd5e8438bdd1e77830c179a4bf29d5ddfc3b6c033fbc3","observation_id":"04cdf0a5-e435-4d52-ae39-10efa6695a7e","resolution":{"observed_at":"2026-08-03T20:34:11.083384Z","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":"2026-08-03T20:34:11.199567Z","title":"Hidden: Hiding data with deep networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:11.199567Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:eb8fba73f19497ae524c6d6586f6c204a3117eccf582decf7f2e9cfc77e7835d","observation_id":"7f3efe70-ef3e-4c9e-b865-f205f4e0e801","resolution":{"observed_at":"2026-08-03T20:34:11.199567Z","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":"2026-08-03T20:34:11.265532Z","title":"Watermark-embedded adversarial examples for copyright protection against diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-03T20:34:11.265532Z"},"links":{"citing_paper":"/paper/2511.19316"},"observation_digest":"sha256:38c9f9cb2ed196ecf241eedc2e790abd02fb6432862a1eaf28a3090b69ffe021","observation_id":"693f4d97-b53c-48a6-8b39-d2c4baebed21","resolution":{"observed_at":"2026-08-03T20:34:11.265532Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2511.19316","last_updated":"2026-05-28T10:21:54Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-03T20:34:06.452227Z","submitted_at":"2025-11-24T17:11:00Z","title":"Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Models: A Comprehensive Benchmark and Removal Approach"},"reference_resolution":{"displayed":47,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":47,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":47},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 0 inbound Pith citation observations for arXiv:2511.19316."}