{"as_of":"2026-08-17T19:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:38fa4395b1ca9ddf8763439f34bb97c63462197c359aaf511c5f5308588ef464","coverage":[{"denominator":80,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":80,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T15:51:18.721280Z","state":"measured"},{"denominator":80,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":80,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+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/2509.21167/citation-record","integrity":"/paper/2509.21167/integrity","json":"/paper/2509.21167/citation-record.json","paper":"/paper/2509.21167"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:51:18.317610Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.317610Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:e43b3d693df38811b268c7542966c4f17e2ba36d9cc7291433abb9776a64275c","observation_id":"9fff0a34-4003-453f-9e5e-0d7934d4aee8","resolution":{"observed_at":"2026-08-15T15:51:18.317610Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.06125","last_updated":"2022-04-13T01:10:33Z","snapshot_observed_at":"2026-08-15T12:50:58.405488Z","submitted_at":"2022-04-13T01:10:33Z","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.06125","snapshot_observed_at":"2026-08-15T15:51:18.323622Z","title":"Hierarchical text-conditional image generation with clip latents.arXiv preprint arXiv:2204.06125, 1(2):3, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.323622Z"},"links":{"cited_paper":"/paper/2204.06125","citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:5ec22d00f5493b4fc05ba621d248e79ac8454711222459870994a837f6447e7e","observation_id":"09ed08df-5a82-4fd3-8ecb-6451350ae24c","resolution":{"observed_at":"2026-08-15T15:51:18.323622Z","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":"2026-08-15T15:51:18.329799Z","title":"Photorealistic text-to-image diffusion models with deep language understanding.Advances in neural information processing systems, 35:36479–36494, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.329799Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:75587350b7e4a75e7e6ca419f10e4bb3e0c0dfb0edb87691805a853d5db8f7c5","observation_id":"d999dc36-e7fb-4140-b47f-18ebf50ff1cb","resolution":{"observed_at":"2026-08-15T15:51:18.329799Z","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":"2026-08-15T15:51:20.047110Z","title":"Laion-5b: An open large-scale dataset for training next generation image-text models.Advances in neural information processing systems, 35:25278–25294, 2022","venue":null,"work_id":"bbc42e90-16d7-4c9e-875a-e1c6fc0c29e0","year":2022},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.334621Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:6fa89d0ee787beae5c5fac8ff090bec8abd25e20623a0f1bc9e06f0f07ea61dd","observation_id":"80360aa5-6258-4877-bfcb-bdea7d7107d2","resolution":{"observed_at":"2026-08-15T15:51:20.052013Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:18.339503Z","title":"Safe latent diffusion: Mitigating inappropriate degeneration in diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.339503Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:4dacb53fe1edcdce34156504f75876812498ee5ead06b65bda67207e2e1f8730","observation_id":"3399162f-7252-4631-98f8-57d74c591b6f","resolution":{"observed_at":"2026-08-15T15:51:18.339503Z","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":"2026-08-15T15:51:18.345052Z","title":"Ai art and its impact on artists","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.345052Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:b60746f127d27bb412f59db259979bc81af9ec1d146543f3776955fe077d4d1c","observation_id":"394ccc50-1ceb-4b41-8e95-7e124c037051","resolution":{"observed_at":"2026-08-15T15:51:18.345052Z","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":"2026-08-15T15:51:18.350879Z","title":"Extracting training data from diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.350879Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:2d801897df4240fe3eae58e49334778b77e0067733fec47a11b9afd325e69f4a","observation_id":"38a12f4e-2050-4216-9c3a-5e2bbfa116ab","resolution":{"observed_at":"2026-08-15T15:51:18.350879Z","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":"2026-08-15T15:51:18.355744Z","title":"Understanding and mitigating copying in diffusion models.Advances in Neural Information Processing Systems, 36:47783–47803, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.355744Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:a0dd61cd55c3132e003cd91475aae9216b215cd0a881ce9bb72f8c3772bf184a","observation_id":"3ed19dca-df7f-408d-a969-011109943b6f","resolution":{"observed_at":"2026-08-15T15:51:18.355744Z","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":"2026-08-15T15:51:18.360891Z","title":"Erasing concepts from diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.360891Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:74436c05c73d087e7cce29f0fe3e45bacdb852b5db8b8fe4353370db489b911a","observation_id":"fbb07ce1-6e2a-435e-93ae-9cf5426de6ee","resolution":{"observed_at":"2026-08-15T15:51:18.360891Z","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":"2026-08-15T15:51:18.366839Z","title":"Ablating concepts in text-to-image diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.366839Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:bc5cfa599fdfd4934b48eb2fa9c8ef18e767433fe00f1399a806ad6f020bcea6","observation_id":"7dff11a2-228e-4570-a387-44af6bc24b96","resolution":{"observed_at":"2026-08-15T15:51:18.366839Z","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":"2026-08-15T15:51:19.972911Z","title":"Receler: Reliable concept erasing of text-to-image diffusion models via lightweight erasers","venue":null,"work_id":"ad77275a-4b80-40d4-8982-304c3215eca0","year":2024},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.371691Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:180690fe9302be010c494298ae83b2f890d1e54139f11533a9399ea2251c99c2","observation_id":"561a91f8-1b67-44ab-9f7b-db66ede311b7","resolution":{"observed_at":"2026-08-15T15:51:19.978029Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.04610","last_updated":"2022-11-10T10:07:37Z","snapshot_observed_at":"2026-08-16T16:27:19.710410Z","submitted_at":"2022-10-03T14:04:46Z","title":"Red-Teaming the Stable Diffusion Safety Filter","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.04610","snapshot_observed_at":"2026-08-15T15:51:18.376426Z","title":"Red-teaming the stable diffusion safety filter.arXiv preprint arXiv:2210.04610, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.376426Z"},"links":{"cited_paper":"/paper/2210.04610","citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:1adabd07096ae990dc5b89b4d4b5f6f90857fb6e65cfe8abc1b77fb1462889d3","observation_id":"d3509639-e5fc-4f3f-8165-5761c4b176fc","resolution":{"observed_at":"2026-08-15T15:51:18.376426Z","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":"2026-08-15T15:51:18.381878Z","title":"Safree: Training-free and adaptive guard for safe text-to-image and video generation.International Conference on Learning Representations, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.381878Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:5443bc8400416b7b1633cedf6e7b0079c0ce02f423aa87ada8907af5045acef0","observation_id":"febb839f-d259-4d6a-8ef1-f04aef4cce6c","resolution":{"observed_at":"2026-08-15T15:51:18.381878Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.15618","last_updated":"2025-05-23T13:25:56Z","snapshot_observed_at":"2026-08-17T14:26:15.519751Z","submitted_at":"2024-10-21T03:40:29Z","title":"Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.15618","snapshot_observed_at":"2026-08-15T15:51:18.387155Z","title":"Erasing undesirable concepts in diffusion models with adversarial preservation.arXiv preprint arXiv:2410.15618, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.387155Z"},"links":{"cited_paper":"/paper/2410.15618","citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:55787a72411a2910e78d5de2997998339a5a843637b0717577c56c22d465c696","observation_id":"1f5aa29a-7860-4797-8d50-5ab2b71871d4","resolution":{"observed_at":"2026-08-15T15:51:18.387155Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.18950","last_updated":"2025-05-23T13:23:21Z","snapshot_observed_at":"2026-08-16T01:15:00.046606Z","submitted_at":"2025-01-31T08:17:23Z","title":"Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.18950","snapshot_observed_at":"2026-08-15T15:51:18.392244Z","title":"Fantastic targets for concept erasure in diffusion models and where to find them.arXiv preprint arXiv:2501.18950, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.392244Z"},"links":{"cited_paper":"/paper/2501.18950","citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:362a54ab61c1e0e50c6ce672fa7d4c2e7532188d941e0551afd2276069a811bc","observation_id":"4b0f7472-fe43-4adf-93de-bcedcd542e3d","resolution":{"observed_at":"2026-08-15T15:51:18.392244Z","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":"2026-08-15T15:51:18.397262Z","title":"Fine-grained erasure in text-to-image diffusion-based foundation models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.397262Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:daf5d6d43c81a5069035bc092bef387c7f0da3037dd56e913966e6d58b3ca0f9","observation_id":"b00045f3-c125-4d05-93cb-0abf910d89a7","resolution":{"observed_at":"2026-08-15T15:51:18.397262Z","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":"2026-08-15T15:51:18.401893Z","title":"Unified concept editing in diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.401893Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:bf2f9b445d5cd7a4b056f28caf6ab6f05275dcae542fa0dc7a2ef6cffefe28c5","observation_id":"33cad3a6-bc9b-42ac-a6a0-b9acef27ccc8","resolution":{"observed_at":"2026-08-15T15:51:18.401893Z","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":"2026-08-15T15:51:18.407965Z","title":"Reliable and efficient concept erasure of text-to-image diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.407965Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:b67ce44db6e816c797ca8e1784820bf5bdd219cbd4be9070d798df679726301e","observation_id":"1c8a051b-3cb9-459c-bab0-18386a8e637f","resolution":{"observed_at":"2026-08-15T15:51:18.407965Z","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":"2026-08-15T15:51:18.412785Z","title":"Mace: Mass concept erasure in diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.412785Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:05aeed7c6030a7b040e6534027b49a8309879cf9925ce726d566505d8a19d084","observation_id":"d3605450-f960-4034-87ef-79016ff2e139","resolution":{"observed_at":"2026-08-15T15:51:18.412785Z","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":"2026-08-15T15:51:19.912582Z","title":"Minimalist concept erasure in generative models","venue":null,"work_id":"b2916a57-b827-4919-a067-39a75cc4dfaf","year":2025},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.417413Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:e1a3a6c3a851f8feb67bd8bb2388f0b5333569fd73d1a8e36a097fc08efd00c4","observation_id":"420410be-66f6-4a01-8e9b-751e0e466fa9","resolution":{"observed_at":"2026-08-15T15:51:19.917142Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:18.421991Z","title":"Unlearning concepts in diffusion model via concept domain correction and concept preserving gradient","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.421991Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:7bb72acfc8d601a7cf6d6f045671e9c722397a3840511f66397bdb494cd541c9","observation_id":"081938d3-bc31-4670-bdad-90a6ad864bdf","resolution":{"observed_at":"2026-08-15T15:51:18.421991Z","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":"2026-08-15T15:51:18.426890Z","title":"Generative adversarial nets.Advances in neural information processing systems, 27, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.426890Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:0d9c1f5d4e7087129bbaa4d9525c73faf4a09ceb5c5eefaebea4db6e7d37c848","observation_id":"e36e347b-61ca-47ea-83a8-4eb9a3935878","resolution":{"observed_at":"2026-08-15T15:51:18.426890Z","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":"2026-08-15T15:51:18.431971Z","title":"Deep unsupervised learning using nonequilibrium thermodynamics","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.431971Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:f1b5a00e9555f0f9672f60de6c3de0b338a594f46533129b7d64f267f09096fc","observation_id":"633ae543-3b9e-4d04-a8f3-9a7a3deeec84","resolution":{"observed_at":"2026-08-15T15:51:18.431971Z","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":"2026-08-15T15:51:19.862404Z","title":"Denoising diffusion probabilistic models.Advances in neural information processing systems, 33:6840–6851, 2020","venue":null,"work_id":"955bb1e2-97d1-45fe-a57a-f78b61866ba8","year":2020},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.437308Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:030b189ff843d319d172d6923c6686b852f3519ec41b7d94277aa41d71dc6fc8","observation_id":"a6055161-e935-4c33-9c75-54ba648cbe35","resolution":{"observed_at":"2026-08-15T15:51:19.868076Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:18.442818Z","title":"A general class of coefficients of divergence of one distribution from another.Journal of the Royal Statistical Society: Series B (Methodological), 28(1):131–142, 1966","venue":null,"work_id":null,"year":1966},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.442818Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:90063314f62af4e6d42b3a5ec1fdd89f57c82a155d547ad9fa06bba37c992d24","observation_id":"7b7c43a2-b430-450c-9d93-482bb942c32b","resolution":{"observed_at":"2026-08-15T15:51:18.442818Z","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":"2026-08-15T15:51:19.835431Z","title":"On information-type measure of difference of probability distributions and indirect observations","venue":null,"work_id":"e59f5ef7-71a1-450b-9bbf-10f6d6f7322e","year":1967},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.447723Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:77eb8ef476e74d4b092c9e7068ef15f82cfc173ca9bd0b884d0e7e9481c4535b","observation_id":"cfce71df-2347-4b1c-8c99-d1ab9c76f90c","resolution":{"observed_at":"2026-08-15T15:51:19.840210Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:19.819506Z","title":"Wainwright, and Michael I","venue":null,"work_id":"56179b11-67c0-4982-ae08-5d172fed5635","year":2010},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.452375Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:615a0dad3c4ac167c44b9b24c6377e1aa883becfb960b496fdf6427885a15501","observation_id":"0c56ce06-9f38-436c-af73-d16d065d18b1","resolution":{"observed_at":"2026-08-15T15:51:19.824419Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:19.804060Z","title":"Mode-seeking divergences: theory and applications to gans","venue":null,"work_id":"3a12dedf-e5ee-47ab-afe1-6e238cd7beb8","year":2023},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.457787Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:e9eb3911475d4e59aace87f3de853df0f295dcf2198d9bff14433483785bc2c8","observation_id":"fffd8a0e-803c-48cf-95d9-55648ee69722","resolution":{"observed_at":"2026-08-15T15:51:19.808635Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:18.462741Z","title":"The illusion of unlearning: The unstable nature of machine unlearning in text-to-image diffusion models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.462741Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:fc5af8d9a3ce02fefdeb1e78696af4191eb0a48c4c5fa798eab114ee27da4015","observation_id":"fc600df7-6054-4ab1-a2f4-8e8337bff729","resolution":{"observed_at":"2026-08-15T15:51:18.462741Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.02747","last_updated":"2023-02-08T15:46:05Z","snapshot_observed_at":"2026-08-16T02:30:42.660030Z","submitted_at":"2022-10-06T08:32:20Z","title":"Flow Matching for Generative Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.02747","snapshot_observed_at":"2026-08-15T15:51:18.467323Z","title":"Flow matching for generative modeling.arXiv preprint arXiv:2210.02747, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.467323Z"},"links":{"cited_paper":"/paper/2210.02747","citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:b46f5dea3955bad7cff3d856c2e090e85d1f1952dff5419fae2f8aba508e5958","observation_id":"e99aef5d-3348-4218-af45-36afd5d3aba5","resolution":{"observed_at":"2026-08-15T15:51:18.467323Z","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":"2026-08-15T15:51:19.780569Z","title":"Springer Verlag, 1985","venue":null,"work_id":"1b73d70d-fc1c-431e-b2c4-d772f7edf9a9","year":1985},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.471940Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:1f92625c731b599d3c83117be6a9c3384b3fcbd82b4c84e1edf0518c6b41108a","observation_id":"d02a4d99-ef14-4713-9ee6-a174d9eaad72","resolution":{"observed_at":"2026-08-15T15:51:19.784837Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:19.766552Z","title":"Analyzingα-divergence in gaussian rate-distortion-perception theory","venue":null,"work_id":"10d9a66b-b5d9-4e3f-b274-fa675f78c54b","year":2024},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.476441Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:90757c01fa8c8f2a8bce9fc5129b80d9b7f5fefaa7b6fb42980bc09285f92f7a","observation_id":"cbb4efb7-ccdc-475b-82ff-b704aa0d9ac1","resolution":{"observed_at":"2026-08-15T15:51:19.771158Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:19.751235Z","title":"On the f-divergences between densities of a multivariate location or scale family.Statistics and Computing, 34(1):60, 2024","venue":null,"work_id":"e34f08bd-6fec-443c-aec0-8e2eb4b00177","year":2024},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.480702Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:714600dd7c1030f2de304dfdb8372c8bfc03d46c3992388cba35497b4d73333d","observation_id":"1ebd41ff-0d91-45ab-8298-59c15a06c70f","resolution":{"observed_at":"2026-08-15T15:51:19.756586Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:19.735543Z","title":"Gradient descent gan optimization is locally stable.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":"770a3e48-d766-4549-8d52-caf87d101dc5","year":2017},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.485084Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:49015e7051ff8c74f25e314163d8adaa016b1ffe08a85a28693c5b801aafa6ae","observation_id":"97d0f4a1-897d-4d1d-abf2-45033c900a31","resolution":{"observed_at":"2026-08-15T15:51:19.740636Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:19.718674Z","title":"Which training methods for gans do actually converge? InInternational conference on machine learning, pages 3481–3490","venue":null,"work_id":"b492aa84-821b-4b86-9cf9-513b2bd93ec9","year":2018},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.489907Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:88c0acb5852fd0b3a901259cd5a62d7b74466abfb5a61de005d207fc24345cca","observation_id":"6452647c-0732-431c-b83b-24041e7dcf27","resolution":{"observed_at":"2026-08-15T15:51:19.723650Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:19.703133Z","title":"Training deep energy-based models with f-divergence minimization","venue":null,"work_id":"eeea9cb4-66a1-4cab-99e6-72c491ad158d","year":2020},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.495800Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:4edf33294c770f1458dc400bc2aecab9074e277efb653a9b0e235a711ff457b3","observation_id":"330db344-8b0a-4428-852d-246e7f517fa3","resolution":{"observed_at":"2026-08-15T15:51:19.708178Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:19.686457Z","title":null,"venue":null,"work_id":"7eb18338-529d-4e5d-85c2-3664d88880b5","year":1996},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.500616Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:b122cd5d4187c3cfb23c3f87b960de5d8b32e3a78c0221bebfeef78649f8d306","observation_id":"2de2622f-53b0-43fc-8524-b63ea0886360","resolution":{"observed_at":"2026-08-15T15:51:19.691584Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:19.669982Z","title":"f-gan: Training generative neural samplers using variational divergence minimization","venue":null,"work_id":"5b936ca3-28e4-40d1-bac1-c6026864f562","year":2016},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.505577Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:aa525a3d16d3e3989345bdf496e7abb8ff4927f5540b6971524cb2a99fb111bd","observation_id":"9d1dd95c-226d-424d-ae45-6fd87f2b72c4","resolution":{"observed_at":"2026-08-15T15:51:19.675851Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.15681","last_updated":"2025-03-09T22:53:27Z","snapshot_observed_at":"2026-08-16T12:56:15.844929Z","submitted_at":"2025-02-21T18:59:20Z","title":"One-step Diffusion Models with $f$-Divergence Distribution Matching","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.15681","snapshot_observed_at":"2026-08-15T15:51:18.510684Z","title":"One-step diffusion models with f-divergence distribution matching","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.510684Z"},"links":{"cited_paper":"/paper/2502.15681","citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:6b871e0ce0c0568746d820ee9849e4c5b21e5494e9b40a2dfdd97357b0588c40","observation_id":"fcf598b8-d41e-49b3-887d-f5072952a159","resolution":{"observed_at":"2026-08-15T15:51:18.510684Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08718","last_updated":"2022-03-23T19:47:21Z","snapshot_observed_at":"2026-07-06T11:01:02.207193Z","submitted_at":"2021-04-18T05:00:29Z","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08718","snapshot_observed_at":"2026-08-15T15:51:18.515817Z","title":"Clipscore: A reference-free evaluation metric for image captioning.arXiv preprint arXiv:2104.08718, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.515817Z"},"links":{"cited_paper":"/paper/2104.08718","citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:63707ce4b172bb3bc6839e622ea2abb23b4ddfd1ee1bf10878066c16f395ec76","observation_id":"d58b16ef-11ab-42a0-9f10-5877d24758c9","resolution":{"observed_at":"2026-08-15T15:51:18.515817Z","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":"2026-08-15T15:51:18.520100Z","title":"Learning transferable visual models from natural language supervision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.520100Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:ff92e518911056e27d3c6c1995ecf886cd864f8ea03a24a472f87df3e614de3b","observation_id":"9d2cf81e-183e-4aa5-bae7-d1ea75a967d9","resolution":{"observed_at":"2026-08-15T15:51:18.520100Z","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":"2026-08-15T15:51:18.524323Z","title":"Sutherland, Michael Arbel, and Arthur Gretton","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.524323Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:c122aa9963065ec316acd94cc719ab7bf69c89f13da20086af3d62bffc5a5a30","observation_id":"59702ccd-fa01-4016-aae7-44dd9b7efb23","resolution":{"observed_at":"2026-08-15T15:51:18.524323Z","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":"2026-08-15T15:51:18.528628Z","title":"Towards making systems forget with machine unlearning","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.528628Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:81c9f906366634f6dcbcddc4f5c1c0742c9e9859bd60a15b986885fe310690b9","observation_id":"58e9d3ad-4bb1-4e3a-b90e-9a886eca1b36","resolution":{"observed_at":"2026-08-15T15:51:18.528628Z","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":"2026-08-15T15:51:18.533520Z","title":"Machine unlearning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.533520Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:c94c2a35ed69729cf06336c96f20208e0cdea1b55794157e0d01f212a90e02ff","observation_id":"c16df87a-3195-4600-a2d4-437fe17a6939","resolution":{"observed_at":"2026-08-15T15:51:18.533520Z","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":"2026-08-15T15:51:18.537950Z","title":"Eternal sunshine of the spotless net: Selective forgetting in deep networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.537950Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:7e9b4bb12e73f041658c53cfa9d75dd7c935ff3c4332af23f097a35e34169549","observation_id":"422ebcbe-8fe2-4e37-a493-58f79e2e1943","resolution":{"observed_at":"2026-08-15T15:51:18.537950Z","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":"2026-08-15T15:51:18.542554Z","title":"Fast yet effective machine unlearning.IEEE Transactions on Neural Networks and Learning Systems, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.542554Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:71737aedf3f54afeda54204b20a2a7400995edb1c310c3965697f719ab72f15f","observation_id":"08e4b3ba-6ee0-44da-92bd-122d0437def3","resolution":{"observed_at":"2026-08-15T15:51:18.542554Z","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":"2026-08-15T15:51:19.596545Z","title":"Can bad teaching induce forgetting? unlearning in deep networks using an incompetent teacher","venue":null,"work_id":"54e1d877-d8d2-4c62-8ac6-5eea7c6665f5","year":2023},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.546733Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:4b88232ba1f28b2ce825bb77f224984a40d92f9cb8e96b48dce44db5a500503e","observation_id":"76ed07be-b492-444f-9fbe-5c9de5d6ea80","resolution":{"observed_at":"2026-08-15T15:51:19.601448Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:18.551933Z","title":"Zero-shot machine unlearning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.551933Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:f976573f55867b1276dabbba3c6dc51bcb34505c098baf1c2bd152d212650f98","observation_id":"5e94e407-aad6-416a-95e2-965650470600","resolution":{"observed_at":"2026-08-15T15:51:18.551933Z","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":"2026-08-15T15:51:19.571336Z","title":"Towards unbounded machine unlearning.Advances in neural information processing systems, 36:1957–1987, 2023","venue":null,"work_id":"e5d7dd41-0e3b-453a-8fc1-9e42a12fd4a1","year":1957},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.556234Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:3dfe0fa4f6b25441466730fca2dc0b54a45d74add968ca7d6704280aa7a14b38","observation_id":"0a8031b8-cdbc-4c42-9d5d-ce4dafe487ad","resolution":{"observed_at":"2026-08-15T15:51:19.576289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2026-08-15T15:51:18.560911Z","title":"Salun: Empowering machine unlearning via gradient-based weight saliency in both image classification and generation.arXiv preprint arXiv:2310.12508, 2023","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.560911Z"},"links":{"cited_paper":"/paper/2310.12508","citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:9c626169303bdf3200db26587e73f06012089a822bcd32104e158b42dde2ee08","observation_id":"8437db92-6d67-49e7-b387-b0966d4c8506","resolution":{"observed_at":"2026-08-15T15:51:18.560911Z","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":"2026-08-15T15:51:19.554622Z","title":"Fast machine unlearning without retraining through selective synaptic dampening","venue":null,"work_id":"b5ef96fc-2837-49cc-a3eb-f017f58447b6","year":2024},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.566157Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:d61a35cd3b2db268b17c5bfa237be673516c259474ae850396d869a0e44d567d","observation_id":"9850b2c0-5440-4068-b936-13f6e54b33af","resolution":{"observed_at":"2026-08-15T15:51:19.560056Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:19.538703Z","title":"Distribution-level feature distancing for machine unlearning: Towards a better trade-off between model utility and forgetting","venue":null,"work_id":"1f47b6d4-f0b7-42be-bada-2cdeb99f423e","year":2025},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.571106Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:82a2ffc19bae09efdd2de548e3135758eb240bed229c88366b5a3a50e16cb19c","observation_id":"96b861f7-ced1-4bd1-8977-e661c27d1d3a","resolution":{"observed_at":"2026-08-15T15:51:19.543920Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:19.522374Z","title":"Lotus: Large-scale machine unlearning with a taste of uncertainty","venue":null,"work_id":"c9341b7f-5a67-46ce-b454-58a909d9f837","year":2025},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.575578Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:d978f7eb4856028169162d32287f25b211f2264a365aff5aca99f5aae70b7853","observation_id":"dd14b4c5-f5c5-49a2-a571-20c9c69bb4f0","resolution":{"observed_at":"2026-08-15T15:51:19.527382Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:19.506142Z","title":"f-scrub: Unbounded machine unlearning via f-divergences","venue":null,"work_id":"1b71be6c-52fb-401f-a13c-6ed250ec9988","year":2025},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.580165Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:0b57dc0fde0a6e27b436b8e371764eb841e318c039b6e4f61890a466298ebd16","observation_id":"d4dfbe3e-9746-4e3e-b236-bfa80f8822d2","resolution":{"observed_at":"2026-08-15T15:51:19.511675Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:19.490971Z","title":"Selective amnesia: A continual learning approach to forgetting in deep generative models.Advances in Neural Information Processing Systems, 36, 2024","venue":null,"work_id":"ede55c9f-9f15-46bc-92d2-795390d39584","year":2024},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.585162Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:df1b54952cb77b2082fc203422dceaa6508534c61f74d4d4ea7d32b05fd67d17","observation_id":"af7844c2-9937-4fe3-82b3-ef031d10d835","resolution":{"observed_at":"2026-08-15T15:51:19.495861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:19.336027Z","title":"Llm unlearning via loss adjustment with only forget data.International Conference on Learning Representations, 2025","venue":null,"work_id":"6ec6c67b-6003-4622-a973-a8900a2e50d6","year":2025},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.590401Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:b1a7bf73f439940af67e7ce877cf1ed78c037519fea97bb0b7f4e4a520172b06","observation_id":"9b8436a0-d51f-4e4f-bbd1-855d2af3de05","resolution":{"observed_at":"2026-08-15T15:51:19.479955Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:18.595458Z","title":"Rethinking machine unlearning for large language models.Nature Machine Intelligence, pages 1–14, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.595458Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:27bb5c1dc1d68f80091e20137281102b34e458d21b0da657c18c3d3900d9bffa","observation_id":"4affa2b7-0885-4548-a21c-d93603fa04ad","resolution":{"observed_at":"2026-08-15T15:51:18.595458Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.10741","last_updated":"2022-03-08T18:18:49Z","snapshot_observed_at":"2026-08-07T12:21:17.790675Z","submitted_at":"2021-12-20T18:42:55Z","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.10741","snapshot_observed_at":"2026-08-15T15:51:18.599890Z","title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.599890Z"},"links":{"cited_paper":"/paper/2112.10741","citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:cb4e5db43edffbd80746f14430b166fcdf1aaabb6ff5eded6d34f7e34a7a7a3d","observation_id":"93da194d-9077-41d0-ba5d-65a0a0bfda73","resolution":{"observed_at":"2026-08-15T15:51:18.599890Z","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":"2026-08-15T15:51:18.605072Z","title":"Diffusion art or digital forgery? investigating data replication in diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.605072Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:71780e6570e3a8cb8699e257216dda6526ba8d64e84c5e4b614137689ab7b3f2","observation_id":"2781354b-8e17-426d-a47b-a44512b1fc3c","resolution":{"observed_at":"2026-08-15T15:51:18.605072Z","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":"2026-08-15T15:51:18.610806Z","title":"One-dimensional adapter to rule them all: Concepts diffusion models and erasing applications","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.610806Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:128d0ca3955c042fb73e7bc1f38f2003809446d72e671ad71c2fe4375edaa0c9","observation_id":"361cd9e5-858c-4b45-b085-396c9d715d9e","resolution":{"observed_at":"2026-08-15T15:51:18.610806Z","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":"2026-08-15T15:51:18.615382Z","title":"Editing implicit assumptions in text-to-image diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.615382Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:4fa03b98359d3e1ab7a7df71eb698c75676cc125ebd0b6144106a72f7fad7c8a","observation_id":"9857e1f1-c045-411f-a29e-3cc7f2a4eee7","resolution":{"observed_at":"2026-08-15T15:51:18.615382Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.07229","last_updated":"2023-08-01T18:41:52Z","snapshot_observed_at":"2026-08-13T02:17:30.405636Z","submitted_at":"2022-10-13T17:55:53Z","title":"Mass-Editing Memory in a Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.07229","snapshot_observed_at":"2026-08-15T15:51:18.619954Z","title":"Mass-editing memory in a transformer.arXiv preprint arXiv:2210.07229, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.619954Z"},"links":{"cited_paper":"/paper/2210.07229","citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:8c73068a738d66861082891a85bc5b5cf207138d9e4bee5a596590b7870d1886","observation_id":"c4ffc06f-a3f6-4571-9b10-8f68dcecb17e","resolution":{"observed_at":"2026-08-15T15:51:18.619954Z","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":"2026-08-15T15:51:19.278168Z","title":"Defensive unlearning with adversarial training for robust concept erasure in diffusion models.Advances in neural information processing systems, 37:36748–36776, 2024","venue":null,"work_id":"3174c0c5-7952-40c1-bd07-a77ccb4e8057","year":2024},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.625292Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:303990b3a72346b3f71d9ec84edbf6d920327ec99334332337da8061d1c21498","observation_id":"04872b87-460b-4b3d-9e0d-b5ac4d77394a","resolution":{"observed_at":"2026-08-15T15:51:19.283151Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:18.630829Z","title":"Efficient fine-tuning and concept suppression for pruned diffusion models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.630829Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:14ca02440c93ac3552cf66d7b4c33932de303319d249ff41ba4a12e7cf41fd71","observation_id":"5ae6cb20-0ca0-40ec-ac01-a2dfb2790952","resolution":{"observed_at":"2026-08-15T15:51:18.630829Z","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":"2026-08-15T15:51:19.253553Z","title":"In International Conference on Machine Learning, pages 38448–38473","venue":null,"work_id":"9b25ebd7-00a6-4218-b6be-644368699df5","year":2024},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.636785Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:d6b6eedd9a90c27786a648ab77b7d637130dea60411162bab1463d0ddc037683","observation_id":"8e075863-c35f-4ffe-99b2-fe08f63d48e0","resolution":{"observed_at":"2026-08-15T15:51:19.258178Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:19.237382Z","title":"When optimizingf-divergence is robust with label noise","venue":null,"work_id":"0f5dcfd5-e72c-4837-bf6a-f574d478c720","year":2021},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.642004Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:40a1414c78287c929040285050c1962fcdd3adf44830bf1b3798b788e35b2fbb","observation_id":"4cf52afc-202d-4e8f-ae62-9f77200dfe4c","resolution":{"observed_at":"2026-08-15T15:51:19.243236Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.06805","last_updated":"2025-04-09T11:52:51Z","snapshot_observed_at":"2026-08-17T10:20:15.760249Z","submitted_at":"2025-04-09T11:52:51Z","title":"Robust Classification with Noisy Labels Based on Posterior Maximization","version":1},"cited_work":{"arxiv_id":"2504.06805","doi":null,"metadata_source":"pith","pith_arxiv_id":"2504.06805","snapshot_observed_at":"2026-08-15T15:51:18.872284Z","title":"Robust Classification with Noisy Labels Based on Posterior Maximization","venue":"cs.LG","work_id":"d401d30c-cd1a-4baf-9529-ace8c9b54fa6","year":2025},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.647303Z"},"links":{"cited_paper":"/paper/2504.06805","citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:01d629b5225535f4f8b177ffe8641d23e5fb42733c8f67cb0a215f9df1b6e940","observation_id":"bc8c78d6-cab0-4332-b6ed-3a5a0c362e06","resolution":{"observed_at":"2026-08-15T15:51:18.878079Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:19.222671Z","title":"Robust semi-supervised learning via f-divergence andα-rényi divergence","venue":null,"work_id":"36a61cbb-e523-44f7-9655-6b87b73efc85","year":2024},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.652764Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:19d41d69643d5455019780f7298a8444e4059caf8d80e655481e35ca41b62abd","observation_id":"a30b671b-e323-4a07-ae4d-83c9ed83215d","resolution":{"observed_at":"2026-08-15T15:51:19.227913Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:19.206542Z","title":"Mutual information estimation via f- divergence and data derangements.Advances in Neural Information Processing Systems, 37:105114–105150, 2024","venue":null,"work_id":"2f2c81c6-57da-4f22-8409-765661f6e96b","year":2024},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.657568Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:db1dad4e44c88fa00f81567ca8f8856e3b963124c184b6c729995d04fb0a7662","observation_id":"f813c11f-3f84-436d-a06a-a060e07cb8e6","resolution":{"observed_at":"2026-08-15T15:51:19.212473Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.18537","last_updated":"2025-06-12T18:32:30Z","snapshot_observed_at":"2026-08-13T20:19:50.789550Z","submitted_at":"2025-01-30T18:06:18Z","title":"Loss Functions and Operators Generated by f-Divergences","version":2},"cited_work":{"arxiv_id":"2501.18537","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.18537","snapshot_observed_at":"2026-08-15T15:51:18.849089Z","title":"Loss Functions and Operators Generated by f-Divergences","venue":"cs.LG","work_id":"aea3cd45-f84a-4e24-986c-50ca4c5c3215","year":2025},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.664234Z"},"links":{"cited_paper":"/paper/2501.18537","citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:3badb9167b84a3f7b2db136fae4c7c9c82fbaa635a719418e759cf4b72a4b487","observation_id":"3d91d26a-8403-4172-affb-e1c530cbc949","resolution":{"observed_at":"2026-08-15T15:51:18.856421Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:18.669117Z","title":"Fine-tuning of diffusion models via stochastic control: entropy regularization and beyond.arXiv preprint arXiv:2403.06279, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.669117Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:42f5cfe83fb2530578acf7c3eaecb14fd7e120b730e3112c4956ee7b9d83decd","observation_id":"8be65072-c2eb-42f4-bb25-9086b5b8f15f","resolution":{"observed_at":"2026-08-15T15:51:18.669117Z","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":"2026-08-15T15:51:19.189988Z","title":"Generalizing alignment paradigm of text-to-image generation with preferences through f-divergence minimization","venue":null,"work_id":"91e501e8-dbc8-4ce9-862e-a7cac431835c","year":2025},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.673745Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:ab8e7a574a0d68ba9dd3973364554e9b7cc856f54859012f7923d605bff592a9","observation_id":"0b3d4029-6249-43c0-bdeb-0a7c5aa146af","resolution":{"observed_at":"2026-08-15T15:51:19.195036Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:19.174628Z","title":"Towards efficient machine unlearning with data augmentation: Guided loss-increasing (gli) to prevent the catastrophic model utility drop","venue":null,"work_id":"62a4931d-57aa-4b42-8f15-09c4b5dff4aa","year":2024},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.677976Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:f27eba71831c254585270c4a97c6823264f5342cf84d773d16a8c1c757f48e56","observation_id":"18a96cd4-9bc4-4eee-ab04-09c67435702a","resolution":{"observed_at":"2026-08-15T15:51:19.179618Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:19.156391Z","title":"Is retain set all you need in machine unlearning? restoring performance of unlearned models with out-of-distribution images","venue":null,"work_id":"4fdad005-fa09-4a2f-9c8e-5eea2e1ffddf","year":2024},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.682512Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:46ff3de00baa5260e6a056edc8180988d0597e045ecca67433c089b238cd7330","observation_id":"a35d7d46-ee12-4647-857d-4739be4cd1e8","resolution":{"observed_at":"2026-08-15T15:51:19.162950Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:19.138313Z","title":"On the f-divergence and singularity of probability measures.Periodica Mathematica Hungarica, 2(1-4):223–234, 1972","venue":null,"work_id":"54fc2fbc-d8d9-4dd4-b979-40d79e9cc722","year":1972},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.688312Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:4b4f6c6a3384d7e8163040548bbe861153dc6016a2e6a29995e36d552e9eaadc","observation_id":"25cc1216-c964-465f-b45d-4d31e2abc183","resolution":{"observed_at":"2026-08-15T15:51:19.144647Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:19.122579Z","title":"Chapman and Hall/CRC, 2018","venue":null,"work_id":"e95d7441-a97b-44a1-b9c5-0e1b3ea0c5ab","year":2018},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.694374Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:6790f42c1b3ff379d42aac897d2490d38a3daf6c5045b2332a60a28b6cdec7be","observation_id":"c8c6de27-e2d5-481b-96d9-60c6fd066a70","resolution":{"observed_at":"2026-08-15T15:51:19.127323Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:18.699330Z","title":"f-gan: Training generative neural samplers using variational divergence minimization.Advances in neural information processing systems, 29, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.699330Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:6db93f07908d9c3497677088ee0021d1655a629cfe17d96bf0858f25a5eb253e","observation_id":"17b105fa-690c-47c6-8997-ae380becab26","resolution":{"observed_at":"2026-08-15T15:51:18.699330Z","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":"2026-08-15T15:51:19.096857Z","title":"f-gail: Learning f-divergence for generative adversarial imitation learning.Advances in neural information processing systems, 33:12805–12815, 2020","venue":null,"work_id":"dea6dac6-3382-487c-ba74-dcd75b5c1dc0","year":2020},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.704400Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:c035100e76091a4e08f68ae4d9ea2be280f7418218baef6129520d9cdb1769fa","observation_id":"e48355f6-682a-4970-9c6c-117c9ff3363d","resolution":{"observed_at":"2026-08-15T15:51:19.102560Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:19.081468Z","title":"concept erasing","venue":null,"work_id":"e7c1c39c-b143-498c-b7ac-9b2291281902","year":2020},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.714303Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:835108c47d3551b51181a1629b9c8a12d1b9077dd536f906992303af9d015540","observation_id":"ce761ea6-ee2a-47d5-a035-d4df393c3b21","resolution":{"observed_at":"2026-08-15T15:51:19.086270Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:51:19.065896Z","title":"Z x(0...ˆt−1) ˆtY t=1 pΦ(xt−1|xt,c) log pΦ(xˆt−1|xˆt,c) pˆΦ(xˆt−1|xˆt,c∗)dx(ˆt−1...0) # dx(ˆt...T) = Z x(ˆt...T) pΦ(x(ˆt...T)|c)","venue":null,"work_id":"06cf853c-d9b1-491c-934c-512fc56fd888","year":2000},"citing_paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence","version":2},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-15T15:51:18.721280Z"},"links":{"citing_paper":"/paper/2509.21167"},"observation_digest":"sha256:4771bfa0a598ffee43834cb42023741148cda69a642d754e517ac44a20200ca5","observation_id":"132a3107-bc6e-4a25-b492-5ddc747c2995","resolution":{"observed_at":"2026-08-15T15:51:19.070625Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2509.21167","last_updated":"2026-05-26T15:43:30Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T13:33:12.687897Z","submitted_at":"2025-09-25T13:51:04Z","title":"A Unified Framework for Diffusion Model Unlearning with f-Divergence"},"reference_resolution":{"displayed":80,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":43,"verified_exact":2,"verified_fuzzy":35},"total_outbound_references":80},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 80 of 80 outbound references and 0 inbound Pith citation observations for arXiv:2509.21167."}