{"as_of":"2026-08-07T11:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e59167b29abac180cd3248fb217a6d4ef358c86d42adea0f0106e74d3223f4ed","coverage":[{"denominator":20,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":20,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T21:27:20.733982Z","state":"measured"},{"denominator":20,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":20,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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/2603.00133/citation-record","integrity":"/paper/2603.00133/integrity","json":"/paper/2603.00133/citation-record.json","paper":"/paper/2603.00133"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.01034","last_updated":"2025-03-02T21:36:04Z","snapshot_observed_at":"2026-08-02T04:37:32.977420Z","submitted_at":"2025-03-02T21:36:04Z","title":"Data Unlearning in Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.01034","snapshot_observed_at":"2026-08-02T21:27:18.851174Z","title":"Data unlearning in diffusion models.arXiv preprint arXiv:2503.01034,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.00133","last_updated":"2026-06-01T15:15:09Z","snapshot_observed_at":"2026-08-07T09:44:34.146120Z","submitted_at":"2026-02-23T17:20:40Z","title":"You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T21:27:18.851174Z"},"links":{"cited_paper":"/paper/2503.01034","citing_paper":"/paper/2603.00133"},"observation_digest":"sha256:90299aad2f1f47079d1174342a1389cd8f2e4ad0ad211760c979225e42fbee61","observation_id":"a7e02d56-52e3-45fb-a5e4-80d4342c1c1c","resolution":{"observed_at":"2026-08-02T21:27:18.851174Z","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":"2026-08-02T21:27:20.050768Z","title":"Robustness of CA Attenuation on Non-Memorized Prompts An important practical question is how memorization miti- gation affects prompts that are not memorized by the model","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.00133","last_updated":"2026-06-01T15:15:09Z","snapshot_observed_at":"2026-08-07T09:44:34.146120Z","submitted_at":"2026-02-23T17:20:40Z","title":"You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-02T21:27:20.050768Z"},"links":{"citing_paper":"/paper/2603.00133"},"observation_digest":"sha256:86a5d90bf84f79b7796faae2e827c787a4f958cb4d6581da8c061e48c21f33a3","observation_id":"f90c13c3-d537-4666-9722-daf8fc4876a5","resolution":{"observed_at":"2026-08-02T21:27:20.050768Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.18052","last_updated":"2025-05-21T21:35:16Z","snapshot_observed_at":"2026-07-06T20:28:09.807683Z","submitted_at":"2025-01-29T23:29:47Z","title":"SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.18052","snapshot_observed_at":"2026-08-02T21:27:18.974138Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.00133","last_updated":"2026-06-01T15:15:09Z","snapshot_observed_at":"2026-08-07T09:44:34.146120Z","submitted_at":"2026-02-23T17:20:40Z","title":"You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T21:27:18.974138Z"},"links":{"cited_paper":"/paper/2501.18052","citing_paper":"/paper/2603.00133"},"observation_digest":"sha256:a09df58511ceef2388bd9e3b1789848a7a75f02bb42053271af9ea70a8f0d1a7","observation_id":"106922a2-0278-4806-8e2e-c5b4ccc8824c","resolution":{"observed_at":"2026-08-02T21:27:18.974138Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21035","last_updated":"2025-01-16T08:08:57Z","snapshot_observed_at":"2026-07-06T18:54:37.159782Z","submitted_at":"2024-07-17T08:19:11Z","title":"Direct Unlearning Optimization for Robust and Safe Text-to-Image Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21035","snapshot_observed_at":"2026-08-02T21:27:19.395757Z","title":"Direct unlearning optimization for robust and safe text-to-image models.arXiv preprint arXiv:2407.21035,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.00133","last_updated":"2026-06-01T15:15:09Z","snapshot_observed_at":"2026-08-07T09:44:34.146120Z","submitted_at":"2026-02-23T17:20:40Z","title":"You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T21:27:19.395757Z"},"links":{"cited_paper":"/paper/2407.21035","citing_paper":"/paper/2603.00133"},"observation_digest":"sha256:e786bd2eb0446d6c844e5e8bf59adfb489b1629bfbb61c03f8fbc340a5e24662","observation_id":"07a2b011-454a-425c-a4a5-be70884b042f","resolution":{"observed_at":"2026-08-02T21:27:19.395757Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.02068","last_updated":"2024-11-04T13:15:28Z","snapshot_observed_at":"2026-08-05T22:33:03.671055Z","submitted_at":"2024-11-04T13:15:28Z","title":"Model Integrity when Unlearning with T2I Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.02068","snapshot_observed_at":"2026-08-02T21:27:19.506756Z","title":"Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C., Wightman, R., Cherti, M., Coombes, T., Katta, A., Mullis, C., Wortsman, M., et al","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.00133","last_updated":"2026-06-01T15:15:09Z","snapshot_observed_at":"2026-08-07T09:44:34.146120Z","submitted_at":"2026-02-23T17:20:40Z","title":"You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T21:27:19.506756Z"},"links":{"cited_paper":"/paper/2411.02068","citing_paper":"/paper/2603.00133"},"observation_digest":"sha256:03997dc255ff64513de6f016ff407e94177fa794571b448091b138414dabdaa6","observation_id":"ef58b18d-71ef-4345-b99e-6fa37d8184dd","resolution":{"observed_at":"2026-08-02T21:27:19.506756Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.15268","last_updated":"2024-10-10T21:27:50Z","snapshot_observed_at":"2026-07-06T16:52:27.457437Z","submitted_at":"2023-11-26T11:12:30Z","title":"Unlearning via Sparse Representations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.15268","snapshot_observed_at":"2026-08-02T21:27:19.621810Z","title":"org/abs/2311.15268","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.00133","last_updated":"2026-06-01T15:15:09Z","snapshot_observed_at":"2026-08-07T09:44:34.146120Z","submitted_at":"2026-02-23T17:20:40Z","title":"You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T21:27:19.621810Z"},"links":{"cited_paper":"/paper/2311.15268","citing_paper":"/paper/2603.00133"},"observation_digest":"sha256:8221525ee20a31082f9fa7d798f6787c105d0b84496baa99c9e7e3e8a5cd1954","observation_id":"494c81fd-c50d-43fd-9134-830013ed6c0b","resolution":{"observed_at":"2026-08-02T21:27:19.621810Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.08694","last_updated":"2023-05-15T14:56:12Z","snapshot_observed_at":"2026-07-06T15:27:21.186782Z","submitted_at":"2023-05-15T14:56:12Z","title":"A Reproducible Extraction of Training Images from Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.08694","snapshot_observed_at":"2026-08-02T21:27:19.758788Z","title":"Diffusion art or digital forgery? investigat- ing data replication in diffusion models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.00133","last_updated":"2026-06-01T15:15:09Z","snapshot_observed_at":"2026-08-07T09:44:34.146120Z","submitted_at":"2026-02-23T17:20:40Z","title":"You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T21:27:19.758788Z"},"links":{"cited_paper":"/paper/2305.08694","citing_paper":"/paper/2603.00133"},"observation_digest":"sha256:583da5dff280dbbf528a9e4408bec58948359db3633e21d3a4ecf721bb9b2bcd","observation_id":"f3dbb0e6-1852-4114-8a3b-9608f8482720","resolution":{"observed_at":"2026-08-02T21:27:19.758788Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11846","last_updated":"2024-10-29T18:36:06Z","snapshot_observed_at":"2026-07-06T17:32:02.824244Z","submitted_at":"2024-02-19T05:25:53Z","title":"UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11846","snapshot_observed_at":"2026-08-02T21:27:19.870621Z","title":"R., Liu, X., et al","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.00133","last_updated":"2026-06-01T15:15:09Z","snapshot_observed_at":"2026-08-07T09:44:34.146120Z","submitted_at":"2026-02-23T17:20:40Z","title":"You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T21:27:19.870621Z"},"links":{"cited_paper":"/paper/2402.11846","citing_paper":"/paper/2603.00133"},"observation_digest":"sha256:f6b98321d30b0380a6f4cfc33189d2f2828c40554a1dd0aadf1a3b152a211d1a","observation_id":"3c49eee2-8177-4cd3-87e0-1513134194d7","resolution":{"observed_at":"2026-08-02T21:27:19.870621Z","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":"2026-08-02T21:27:19.974522Z","title":"Appendix Contents A.1 Limitations","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.00133","last_updated":"2026-06-01T15:15:09Z","snapshot_observed_at":"2026-08-07T09:44:34.146120Z","submitted_at":"2026-02-23T17:20:40Z","title":"You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T21:27:19.974522Z"},"links":{"citing_paper":"/paper/2603.00133"},"observation_digest":"sha256:da1f437286f2dec465ec9f157f44de2aa4bfffc841f989d9503e0a89d0baa3e8","observation_id":"3bd906e3-33c7-4e02-824f-6bf7850b0c69","resolution":{"observed_at":"2026-08-02T21:27:19.974522Z","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":"2026-08-02T21:27:20.131437Z","title":"positive targets","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.00133","last_updated":"2026-06-01T15:15:09Z","snapshot_observed_at":"2026-08-07T09:44:34.146120Z","submitted_at":"2026-02-23T17:20:40Z","title":"You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T21:27:20.131437Z"},"links":{"citing_paper":"/paper/2603.00133"},"observation_digest":"sha256:d212b6d03960488ef0db6837dc96b7ad49b387ed2af7acae53a5880a7fd2d69a","observation_id":"b772f064-149e-4149-b32f-0a3336a88e55","resolution":{"observed_at":"2026-08-02T21:27:20.131437Z","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":"2026-08-02T21:27:20.218962Z","title":"no mitiga- tion","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.00133","last_updated":"2026-06-01T15:15:09Z","snapshot_observed_at":"2026-08-07T09:44:34.146120Z","submitted_at":"2026-02-23T17:20:40Z","title":"You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T21:27:20.218962Z"},"links":{"citing_paper":"/paper/2603.00133"},"observation_digest":"sha256:8ea1e63ce0608f9f7a770146f80245655e19e94ce21de4a518087aa7963de901","observation_id":"c63a7814-d631-4ae7-8af9-6add2c7c12e3","resolution":{"observed_at":"2026-08-02T21:27:20.218962Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-02T21:27:20.303773Z","title":"Specifically, we construct SSCD-CLIP and SSCD-FID Pareto frontiers for each model version and memorization type setting","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.00133","last_updated":"2026-06-01T15:15:09Z","snapshot_observed_at":"2026-08-07T09:44:34.146120Z","submitted_at":"2026-02-23T17:20:40Z","title":"You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T21:27:20.303773Z"},"links":{"citing_paper":"/paper/2603.00133"},"observation_digest":"sha256:e290ec6868816b0fef417eff371be6f1e02e29a0b683d9cbf9c2d37afb29b444","observation_id":"f204250f-1482-48bd-95ad-3c5ea876195d","resolution":{"observed_at":"2026-08-02T21:27:20.303773Z","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":"2026-08-02T21:27:20.488421Z","title":"The advantage is particularly notable for the SSCD-CLIP trade-off, where both CA at- tenuation and CA-in-GUARD consistently dominate other methods","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.00133","last_updated":"2026-06-01T15:15:09Z","snapshot_observed_at":"2026-08-07T09:44:34.146120Z","submitted_at":"2026-02-23T17:20:40Z","title":"You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T21:27:20.488421Z"},"links":{"citing_paper":"/paper/2603.00133"},"observation_digest":"sha256:717f42022b877cb75122c3248e8d7120baad04534b11315ecf4b73b91afd7de7","observation_id":"4eb0b44f-aa31-4366-8c44-04cf6aaf347a","resolution":{"observed_at":"2026-08-02T21:27:20.488421Z","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":"2026-08-02T21:27:20.578414Z","title":"Lower scores indicate weaker similarity to the training set and therefore less memorization","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.00133","last_updated":"2026-06-01T15:15:09Z","snapshot_observed_at":"2026-08-07T09:44:34.146120Z","submitted_at":"2026-02-23T17:20:40Z","title":"You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T21:27:20.578414Z"},"links":{"citing_paper":"/paper/2603.00133"},"observation_digest":"sha256:3ea6e7abc57df323294efa2181b2458b2c779a87b080323b1fcf9e6d46c96624","observation_id":"602ea8e4-1172-4021-b392-f4a2d4e77927","resolution":{"observed_at":"2026-08-02T21:27:20.578414Z","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":"2026-08-02T21:27:20.733982Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.00133","last_updated":"2026-06-01T15:15:09Z","snapshot_observed_at":"2026-08-07T09:44:34.146120Z","submitted_at":"2026-02-23T17:20:40Z","title":"You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T21:27:20.733982Z"},"links":{"citing_paper":"/paper/2603.00133"},"observation_digest":"sha256:49649ed8d83bbdb786d55b93fb5f65ad7be711861009b0cf73297ba5fd7da236","observation_id":"fa51f47f-365b-4a58-b61c-682541070eb9","resolution":{"observed_at":"2026-08-02T21:27:20.733982Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.13356","last_updated":"2025-03-17T07:46:49Z","snapshot_observed_at":"2026-08-01T17:13:21.519528Z","submitted_at":"2024-06-19T09:03:21Z","title":"Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.13356","snapshot_observed_at":"2026-08-02T21:27:19.216947Z","title":"S., and Smith, V","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.00133","last_updated":"2026-06-01T15:15:09Z","snapshot_observed_at":"2026-08-07T09:44:34.146120Z","submitted_at":"2026-02-23T17:20:40Z","title":"You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models","version":2},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-02T21:27:19.216947Z"},"links":{"cited_paper":"/paper/2406.13356","citing_paper":"/paper/2603.00133"},"observation_digest":"sha256:27ed619ab4567dc48610d20f9b5444a9202e96e5e71dc477f0b220def2fd7b36","observation_id":"535f61ff-3636-46a6-8f3d-32274d53a160","resolution":{"observed_at":"2026-08-02T21:27:19.216947Z","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":"2026-08-02T21:27:19.153990Z","title":"Adjusting initial noise to mitigate memorization in text-to-image dif- fusion models.arXiv preprint arXiv:2510.08625,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.00133","last_updated":"2026-06-01T15:15:09Z","snapshot_observed_at":"2026-08-07T09:44:34.146120Z","submitted_at":"2026-02-23T17:20:40Z","title":"You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-02T21:27:19.153990Z"},"links":{"citing_paper":"/paper/2603.00133"},"observation_digest":"sha256:4b9c4594ba703d5845d08c2a7ab5857facbc0d41f3df1e69880a5f22d7b7f11f","observation_id":"ff3d4cac-bd9e-427e-8c3d-e38fac1ca59d","resolution":{"observed_at":"2026-08-02T21:27:19.153990Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.18025","last_updated":"2025-05-31T19:22:41Z","snapshot_observed_at":"2026-07-06T19:22:54.212921Z","submitted_at":"2024-09-26T16:32:19Z","title":"An Adversarial Perspective on Machine Unlearning for AI Safety","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.18025","snapshot_observed_at":"2026-08-02T21:27:19.292306Z","title":"An adversarial perspective on machine 10 Surgical Memorization Mitigation in Text-to-Image Diffusion Models unlearning for ai safety.arXiv preprint arXiv:2409.18025,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.00133","last_updated":"2026-06-01T15:15:09Z","snapshot_observed_at":"2026-08-07T09:44:34.146120Z","submitted_at":"2026-02-23T17:20:40Z","title":"You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-02T21:27:19.292306Z"},"links":{"cited_paper":"/paper/2409.18025","citing_paper":"/paper/2603.00133"},"observation_digest":"sha256:20543d62666f48057311262e1af5489d27cdb30135251d3efc8c6382384b887a","observation_id":"d560bdf5-77c4-4315-ba8b-052c1424b66a","resolution":{"observed_at":"2026-08-02T21:27:19.292306Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.12508","last_updated":"2024-04-04T07:45:38Z","snapshot_observed_at":"2026-08-03T17:30:25.153454Z","submitted_at":"2023-10-19T06:17:17Z","title":"SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.12508","snapshot_observed_at":"2026-08-02T21:27:19.083449Z","title":"Gandikota, R., Materzynska, J., Fiotto-Kaufman, J., and Bau, D","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.00133","last_updated":"2026-06-01T15:15:09Z","snapshot_observed_at":"2026-08-07T09:44:34.146120Z","submitted_at":"2026-02-23T17:20:40Z","title":"You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-02T21:27:19.083449Z"},"links":{"cited_paper":"/paper/2310.12508","citing_paper":"/paper/2603.00133"},"observation_digest":"sha256:37068669f47489b35dd089e5168ee7a3f7597b6101a97ded9308720f1d7a8bd1","observation_id":"0bca2805-20b0-4452-be2a-5ccf3e406c85","resolution":{"observed_at":"2026-08-02T21:27:19.083449Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.11219","last_updated":"2025-03-02T01:07:41Z","snapshot_observed_at":"2026-08-06T23:01:37.855520Z","submitted_at":"2024-09-17T14:12:50Z","title":"Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.11219","snapshot_observed_at":"2026-08-02T21:27:18.901155Z","title":"Cywi´nski, B","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.00133","last_updated":"2026-06-01T15:15:09Z","snapshot_observed_at":"2026-08-07T09:44:34.146120Z","submitted_at":"2026-02-23T17:20:40Z","title":"You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models","version":2},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-02T21:27:18.901155Z"},"links":{"cited_paper":"/paper/2409.11219","citing_paper":"/paper/2603.00133"},"observation_digest":"sha256:cbd04cbd51fe535e4a2ff9b1023fba88b0a5ef3642e158b70156668ebf0cc2ab","observation_id":"3edc99b9-0624-40ed-8ed2-100b1713175d","resolution":{"observed_at":"2026-08-02T21:27:18.901155Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2603.00133","last_updated":"2026-06-01T15:15:09Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T09:44:34.146120Z","submitted_at":"2026-02-23T17:20:40Z","title":"You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models"},"reference_resolution":{"displayed":20,"state_counts":{"malformed_identifier":2,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":18,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":20},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 0 inbound Pith citation observations for arXiv:2603.00133."}