{"as_of":"2026-08-08T09:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f29d71cbe589c409faf11956efb1cd7ce1808e9f528efb86896833a97b71cea0","coverage":[{"denominator":36,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":36,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:26:09.569617Z","state":"measured"},{"denominator":36,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":36,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2505.21848/citation-record","integrity":"/paper/2505.21848/integrity","json":"/paper/2505.21848/citation-record.json","paper":"/paper/2505.21848"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-07T13:26:04.759240Z","title":"GPT-4 technical report","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:04.759240Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:41c508bdf0609a513731a0f4dda6fbd04c6f5bbdbc7c63f63e7f09f368d4424f","observation_id":"761a0c53-34ef-40e4-a4c7-61a99729d7e7","resolution":{"observed_at":"2026-08-07T13:26:04.759240Z","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":"2026-08-07T13:26:14.968962Z","title":"Extracting training data from diffu- sion models","venue":null,"work_id":"f0cec08c-c46b-4d66-aae4-1f246b849181","year":2023},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:04.824101Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:dfb39d079c668e4d8e292adab8749bfadbb5eabf8c330d20ec144a1187b9fe76","observation_id":"e5e64a7d-ff12-43ae-9612-69518edb119f","resolution":{"observed_at":"2026-08-07T13:26:15.016806Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.21665","last_updated":"2025-04-25T03:20:52Z","snapshot_observed_at":"2026-07-06T19:41:15.267950Z","submitted_at":"2024-10-29T02:16:01Z","title":"Exploring Local Memorization in Diffusion Models via Bright Ending Attention","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.21665","snapshot_observed_at":"2026-08-07T13:26:04.866637Z","title":"Exploring local memorization in diffusion models via bright ending attention","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:04.866637Z"},"links":{"cited_paper":"/paper/2410.21665","citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:eb97f11bb36a050709cf67e2ef302105752e6c667ab73dfcb1d41a9814167d81","observation_id":"a9d3123b-d74d-48c3-b23a-20c9e87b3183","resolution":{"observed_at":"2026-08-07T13:26:04.866637Z","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":"2026-08-07T13:26:14.788779Z","title":"Towards memorization-free diffusion models","venue":null,"work_id":"03ab8cdc-04d5-4221-8e40-06e07827fb40","year":2024},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:04.945354Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:6f899d10d2fb8f2943c66f14cc00bcad3fd99b42c021aa7d8cc93da88fc6e6d2","observation_id":"7264fcba-cdcf-4e2e-bee9-c1bd33a5770c","resolution":{"observed_at":"2026-08-07T13:26:14.871356Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.10555","last_updated":"2020-03-23T21:17:42Z","snapshot_observed_at":"2026-08-06T14:37:14.514749Z","submitted_at":"2020-03-23T21:17:42Z","title":"ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.10555","snapshot_observed_at":"2026-08-07T13:26:04.995050Z","title":"ELECTRA: Pre-training text encoders as discriminators rather than generators","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:04.995050Z"},"links":{"cited_paper":"/paper/2003.10555","citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:dff7f8696353e9e01188f77ade8e1ea27e3d3e25c6e8015a284f55b68d6a7be7","observation_id":"3b310a8d-023f-4e9e-b88c-ef9747117450","resolution":{"observed_at":"2026-08-07T13:26:04.995050Z","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":"2026-08-07T13:26:14.625058Z","title":"Diffusion models beat GANs on image synthesis","venue":null,"work_id":"227d3f5b-9f71-46b5-9b40-0b70ba2c75cf","year":2021},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:05.052080Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:ea2a4cc510edd9fbca5928edba082908698e1329b05dc9dd71b2d5a88a063b0f","observation_id":"33b8e1f5-36ca-4f65-bb1f-9547eeeb5d48","resolution":{"observed_at":"2026-08-07T13:26:14.708574Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:26:14.409767Z","title":"On the inherent regulariza- tion effects of noise injection during training","venue":null,"work_id":"d42c5851-2dd6-4e0e-9998-1469a7f59fe6","year":2021},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:05.098898Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:90ef2ecd07e3c4c9929d300732d8f201dd2543f911b8850d93594e83067e2ae3","observation_id":"6623414f-75c2-4e62-b91d-b6ebadc06015","resolution":{"observed_at":"2026-08-07T13:26:14.514225Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:26:05.175525Z","title":"Generative adversarial networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:05.175525Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:ae8c3a68a355f3de9e676a18689c890682fb0ba450644c674b847a4a45d4e90a","observation_id":"fbd8452d-0b49-45d6-909c-8cecbc3c7f93","resolution":{"observed_at":"2026-08-07T13:26:05.175525Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.02664","last_updated":"2025-02-20T06:17:25Z","snapshot_observed_at":"2026-08-05T08:58:57.183527Z","submitted_at":"2023-10-04T09:04:20Z","title":"On Memorization in Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.02664","snapshot_observed_at":"2026-08-07T13:26:05.238193Z","title":"On memorization in diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:05.238193Z"},"links":{"cited_paper":"/paper/2310.02664","citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:4490c8c854a039b6e3ddb3f426b8450b66518338ebecbd86dfd5a30ddcfdad99","observation_id":"852b3feb-c1df-4bb7-825a-c03e91374bf1","resolution":{"observed_at":"2026-08-07T13:26:05.238193Z","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":"2026-08-07T13:26:14.204084Z","title":"Finding NeMo: Localizing neurons responsible for memorization in diffu- sion models","venue":null,"work_id":"8de24e57-7f75-4172-9a90-d9a7e2d6287f","year":2024},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:05.307600Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:34abde9375ac3da8a25641c1e4c61f6b22de1b2aa4edea646912edf2820da63c","observation_id":"4442f910-edc3-4b23-94f8-0eced1df83fa","resolution":{"observed_at":"2026-08-07T13:26:14.286829Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:26:05.427660Z","title":"Denoising dif- fusion probabilistic models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:05.427660Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:4cec634fcc9d4ec232979d6c7a8642acec7bf8859611622ae02ae7acbb05d83a","observation_id":"ac07fae5-7d12-43a9-9c1b-867dd36b8b16","resolution":{"observed_at":"2026-08-07T13:26:05.427660Z","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":"2026-08-07T13:26:13.997786Z","title":"An introduction to variational autoencoders","venue":null,"work_id":"ee6ff8c4-8e38-4f5c-bddf-793c8e1e99c9","year":2019},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:05.507707Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:b46573ebb817b0f1d8aa57a73964afa633b846ba30c0928533d733de98895f2a","observation_id":"39410939-c8c4-4110-b76c-6b0c56f5c448","resolution":{"observed_at":"2026-08-07T13:26:14.082907Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.02692","last_updated":"2021-06-24T11:31:55Z","snapshot_observed_at":"2026-07-06T11:06:54.962664Z","submitted_at":"2021-05-06T14:12:26Z","title":"Learning to Perturb Word Embeddings for Out-of-distribution QA","version":3},"cited_work":{"arxiv_id":"2105.02692","doi":null,"metadata_source":"pith","pith_arxiv_id":"2105.02692","snapshot_observed_at":"2026-08-07T13:26:10.494971Z","title":"Learning to Perturb Word Embeddings for Out-of-distribution QA","venue":"cs.CL","work_id":"59a4ce41-cb8d-45b4-bc78-36e0344ef9b3","year":2021},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:05.590048Z"},"links":{"cited_paper":"/paper/2105.02692","citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:d45052946eb410d420e028e043a59238d9cfc0b56b636c63ebd8ac25a8e24d48","observation_id":"08071358-c136-4118-918b-b4b498dd3698","resolution":{"observed_at":"2026-08-07T13:26:10.565999Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:26:13.836577Z","title":"Mitigate replication and copying in diffusion mod- els with generalized caption and dual fusion enhancement","venue":null,"work_id":"d618be4b-2887-46d2-b5f4-2d928d033bc5","year":2024},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:05.699219Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:572295580370bb49bdbfa652c59b7333888e76881784b78315c99c3304f98989","observation_id":"8c771320-e440-4ef5-9792-1d2dd404a58e","resolution":{"observed_at":"2026-08-07T13:26:13.917759Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.01118","last_updated":"2024-12-02T04:41:30Z","snapshot_observed_at":"2026-07-06T19:59:56.438747Z","submitted_at":"2024-12-02T04:41:30Z","title":"LoyalDiffusion: A Diffusion Model Guarding Against Data Replication","version":1},"cited_work":{"arxiv_id":"2412.01118","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.01118","snapshot_observed_at":"2026-08-07T13:26:10.289003Z","title":"LoyalDiffusion: A Diffusion Model Guarding Against Data Replication","venue":"cs.CV","work_id":"071e0735-8a19-4a75-90ba-4584d9665615","year":2024},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:05.740848Z"},"links":{"cited_paper":"/paper/2412.01118","citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:b76816cdf8ea0c5e9d2701626e17b78dd56b1947f5f294e7b559f3235bba8a31","observation_id":"8b84adb6-66e6-4b45-8888-63927fdf6077","resolution":{"observed_at":"2026-08-07T13:26:10.406749Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:26:13.663645Z","title":"Are GANs created equal? A large-scale study","venue":null,"work_id":"6722d822-545d-4c92-9093-9a0203adc7b8","year":2018},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:05.810758Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:df7dcb4226e19210ea7431360118f4c9f577401cd76bfa1dd9458a44d79fac41","observation_id":"14eaab51-6911-4d9f-a476-ac9d66618601","resolution":{"observed_at":"2026-08-07T13:26:13.788866Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:26:13.460719Z","title":"Enhancing DreamBooth with LoRA for generating unlimited characters with Stable Dif- fusion","venue":null,"work_id":"19d24cec-cf46-49d6-abba-8c0cfe0efa0f","year":2024},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:05.867247Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:98a3eee99c9cf9ae4fb60c1e842774e78c5507ec67f337dda8321792ef965102","observation_id":"c9b655f0-a86a-4867-861f-72214a75f697","resolution":{"observed_at":"2026-08-07T13:26:13.557917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:26:13.247245Z","title":"A self-supervised descriptor for image copy detection","venue":null,"work_id":"316f867d-505d-496e-a708-4f380362e3c9","year":2022},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:05.899381Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:0d61895c09d40be745bd435bebd63a8eafb96a259c364c1d28c71b9f157b506c","observation_id":"1c57f15e-6199-42e8-9215-3263304de062","resolution":{"observed_at":"2026-08-07T13:26:13.372725Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:26:13.125937Z","title":"Learning transferable visual models from natural language supervi- sion","venue":null,"work_id":"05bf722b-5a10-4861-85ff-0bb0a6aaeac9","year":2021},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:05.969966Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:af35b316f2ed5245745132dc4f31bc21c5de31fcd4c8fce240fc4278424b6b50","observation_id":"4b6deddd-8e59-4ed6-a513-5313eb165eee","resolution":{"observed_at":"2026-08-07T13:26:13.152408Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:26:06.045871Z","title":"Zero-shot text-to-image generation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:06.045871Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:b00c5b43955030826057817db2bdde2f3981d7fbe00567bdabaa3d1591a6105f","observation_id":"f6d62584-30ba-4731-86a7-fd34bdd03346","resolution":{"observed_at":"2026-08-07T13:26:06.045871Z","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":"2026-08-07T13:26:12.955595Z","title":"Unveiling and mitigating mem- orization in text-to-image diffusion models through cross at- tention","venue":null,"work_id":"b2db4645-1f8a-42f7-a81d-229faa952916","year":2024},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:06.097339Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:7910a49aeee04d035e05d62fc01e79e6ad02f16e30843dc2e361e6b258a50dfc","observation_id":"9fceadd2-fe27-4a32-a02c-9be7d469da71","resolution":{"observed_at":"2026-08-07T13:26:13.045332Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:26:12.707080Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":"17b76c12-2511-4271-b62d-5af0ff1fd5c1","year":2022},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:06.188552Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:9d88ec7bc2b1ce98e2f83ca089d69afe885758ed673a43b71741c7ceef3dd3d7","observation_id":"46db90c4-eb2f-4587-af1f-74ee3a8450ee","resolution":{"observed_at":"2026-08-07T13:26:12.817834Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:26:12.561831Z","title":"U- Net: Convolutional networks for biomedical image segmen- tation","venue":null,"work_id":"184c4cf9-da3f-4a16-bca8-2aa22daff95f","year":2015},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:06.320767Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:8af843d092a61b0aa5b0ba4bf60d31a767fde18377cf05ecaa80a301e538d138","observation_id":"5f0d1f3e-4d0b-40d6-b42a-8dcd01d89d78","resolution":{"observed_at":"2026-08-07T13:26:12.627034Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:26:06.386324Z","title":"Photorealistic text-to-image diffusion models with deep language understanding","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:06.386324Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:39967abbbc7c767b448451b5e02cdb900d01bba05da3bf6f6dc2fd6533d10246","observation_id":"599dab5a-7a1f-40e2-895e-e7f0b1814d74","resolution":{"observed_at":"2026-08-07T13:26:06.386324Z","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":"2026-08-07T13:26:12.292560Z","title":"Safe latent diffusion: Mitigating inappro- priate degeneration in diffusion models","venue":null,"work_id":"9b509db0-2ea9-432d-a786-996824d590f9","year":2023},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:06.486663Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:b7e61bc8c5c3040d25e50357373b9edf65aac2a79cb64d7111317feee1d42e12","observation_id":"567930b9-1d68-4e7a-9e56-4385b0e1709d","resolution":{"observed_at":"2026-08-07T13:26:12.410737Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:26:12.063370Z","title":"LAION-5B: An open large-scale dataset for train- ing next generation image-text models","venue":null,"work_id":"d5c0701f-0e0a-4dce-9cee-db64bd010b6b","year":2022},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:06.558213Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:83a25d14e588f047cd638f01cd95f2c848aba0cc83ccbf28f9ca78ae6df38c73","observation_id":"38404cab-097b-44f5-8e78-f0e0656d0244","resolution":{"observed_at":"2026-08-07T13:26:12.155278Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:26:11.863894Z","title":"Diffusion art or digital forgery? Investigating data replication in diffusion models","venue":null,"work_id":"ffd91a5d-0a74-4508-a8da-ae1d477f8a10","year":2023},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:06.645051Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:152eb57c0d35f4e43a43f7859b3eb90e00efa2e4d17506d5c2658a5721eb1d0a","observation_id":"8cab64d3-a69e-4c86-8b13-269b754d6662","resolution":{"observed_at":"2026-08-07T13:26:11.909731Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:26:11.625859Z","title":"Understanding and mitigating copying in diffusion models","venue":null,"work_id":"90d17300-1163-4dc2-91d8-83939796ae68","year":2023},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:06.790991Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:e872e65f48145e224a57e2fcc0bfa0190a68281c5fd39e9e3bc0002ed3c8faa3","observation_id":"be1d0a5f-ca93-4a2d-b62f-687893797314","resolution":{"observed_at":"2026-08-07T13:26:11.746969Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-07T13:26:06.891309Z","title":"LLaMA: Open and efficient foundation language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:06.891309Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:b26d0e59ca5c8117b683537e51f365d0a65324f2a70773198fd38cc19a31c723","observation_id":"b409235e-9eb1-460b-829f-e62bcf6b64fe","resolution":{"observed_at":"2026-08-07T13:26:06.891309Z","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":"2026-08-07T13:26:11.412175Z","title":"Lexical density and register differentiation","venue":null,"work_id":"8d230fa3-01c7-4f34-8923-396c6086ecbf","year":1971},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:06.983320Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:1d4d6e05a5b2c7ce6e79e609dc95f34071f178a2c613b90a78becb63a075debe","observation_id":"413470f1-02b7-4ede-a2a7-1093cc5ccf6d","resolution":{"observed_at":"2026-08-07T13:26:11.519522Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.12733","last_updated":"2023-03-17T17:39:06Z","snapshot_observed_at":"2026-07-06T15:06:45.725032Z","submitted_at":"2023-03-17T17:39:06Z","title":"On the De-duplication of LAION-2B","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.12733","snapshot_observed_at":"2026-08-07T13:26:07.125999Z","title":"On the de-duplication of LAION-2B","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:07.125999Z"},"links":{"cited_paper":"/paper/2303.12733","citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:da4cd2533f32c6697522d9e380cb5505d947e42f5f97617e66328425e68d291f","observation_id":"d839a434-63c4-40d9-a0bb-158f40c9ec1e","resolution":{"observed_at":"2026-08-07T13:26:07.125999Z","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":"2026-08-07T13:26:11.180404Z","title":"De- tecting, explaining, and mitigating memorization in diffusion models","venue":null,"work_id":"7072d793-3bb5-4281-bc43-9ee1993fb7a5","year":2024},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:07.297168Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:66c440591d2f0adaea55eae865adf09439833aa0f108f10c41f2426b43738b09","observation_id":"92569f82-d648-4a55-831b-58af7b5df925","resolution":{"observed_at":"2026-08-07T13:26:11.281506Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2211.08099","last_updated":"2023-06-06T03:01:43Z","snapshot_observed_at":"2026-07-06T14:18:30.314936Z","submitted_at":"2022-11-15T12:33:31Z","title":"A Universal Discriminator for Zero-Shot Generalization","version":2},"cited_work":{"arxiv_id":"2211.08099","doi":null,"metadata_source":"pith","pith_arxiv_id":"2211.08099","snapshot_observed_at":"2026-08-07T13:26:10.119415Z","title":"A Universal Discriminator for Zero-Shot Generalization","venue":"cs.CL","work_id":"c816e7bf-29e8-4f6d-b2cd-10a248e38a19","year":2022},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:07.510193Z"},"links":{"cited_paper":"/paper/2211.08099","citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:b54280004c3939c58cd911e089baf998d70f28589bd24c44db3a67dc6e815897","observation_id":"6911a96d-ba42-4a1a-9cbe-d3469b86625a","resolution":{"observed_at":"2026-08-07T13:26:10.169450Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:26:11.021862Z","title":"Infusion: Preventing customized text-to-image diffusion from overfitting","venue":null,"work_id":"0b07e839-0105-4d41-9f71-1c32600cb762","year":2024},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:07.965105Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:780069594cf48aa30eeff9572e479b0135a94fe5aad4b73ee7b466fd1eebcf03","observation_id":"04aa0093-6d13-4d35-a698-61be745e622f","resolution":{"observed_at":"2026-08-07T13:26:11.103060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:26:10.831574Z","title":"Forget-Me-Not: Learning to for- get in text-to-image diffusion models","venue":null,"work_id":"6311bdba-bdbc-46bc-bb9d-e3037d51374f","year":2024},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:08.570716Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:0a63f435b58d162d88995c1c5075f14c6910738cd617e1fdc8d77172c0698b02","observation_id":"ee20f7fb-9666-427a-b8ad-ecd1a241a84a","resolution":{"observed_at":"2026-08-07T13:26:10.912001Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:26:10.699350Z","title":"For the inference process, we generate sam- ples using S = 50 steps, uniformly spacing across the full diffusion process","venue":null,"work_id":"12a51a6b-5750-41f2-ad8a-7bd057b390fc","year":null},"citing_paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings","version":1},"reference_index":256,"source":"pdf_text","source_observed_at":"2026-08-07T13:26:09.569617Z"},"links":{"citing_paper":"/paper/2505.21848"},"observation_digest":"sha256:cbd022189d113607a1ba5edbe25711c40863cc14e279a5123c91a0e619b851db","observation_id":"d22c370d-605d-4389-be10-44fd4cb9c223","resolution":{"observed_at":"2026-08-07T13:26:10.768749Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.21848","last_updated":"2025-05-28T00:29:20Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T13:19:15.329718Z","submitted_at":"2025-05-28T00:29:20Z","title":"FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings"},"reference_resolution":{"displayed":36,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":10,"verified_exact":3,"verified_fuzzy":23},"total_outbound_references":36},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 0 inbound Pith citation observations for arXiv:2505.21848."}