{"as_of":"2026-08-22T16:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:77cb2afff21268a08c4e7894aea1e7af01def53cf973dac80f6b2a4d75908197","coverage":[{"denominator":135,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T19:21:35.091249Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+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/2506.16961/citation-record","integrity":"/paper/2506.16961/integrity","json":"/paper/2506.16961/citation-record.json","paper":"/paper/2506.16961"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:21:34.745454Z","title":"A high-quality denoising dataset for smartphone cameras","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.745454Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:aefca7bb504cfeb23c8db5ecc02429bc6750c00b642001998a8e03027d4494ca","observation_id":"1b8fa1e9-04aa-4620-a70b-6f2bf94e67d9","resolution":{"observed_at":"2026-08-15T19:21:34.745454Z","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":"2026-08-15T19:21:34.749844Z","title":"Defocus de- blurring using dual-pixel data","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.749844Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:daf3f92c329ca66e7f3a11e2b02e3ba1a5263cb0861a5faae9af69e9cabc5a48","observation_id":"292fffb3-7232-4bf5-b567-303d82615018","resolution":{"observed_at":"2026-08-15T19:21:34.749844Z","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":"2026-08-15T19:21:34.754128Z","title":"Ntire 2017 challenge on single image super-resolution: Dataset and study","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.754128Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:3c7d8580e5d1a4a651fc4a96639c14b673f9d8d673d4bb64c19d703592a89b6f","observation_id":"607d53a8-793d-4ae9-899c-e122f8a7b1c5","resolution":{"observed_at":"2026-08-15T19:21:34.754128Z","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":"2026-08-15T19:21:34.757967Z","title":"Dense-haze: A benchmark for image dehazing with dense-haze and haze-free images","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.757967Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:1e91ad95de4bb3ff5c8704b03ec22bb317581be124b88e48c014c2847deee149","observation_id":"3a6ea731-3183-46d2-998c-9a8a4760aebd","resolution":{"observed_at":"2026-08-15T19:21:34.757967Z","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":"2026-08-15T19:21:34.762119Z","title":"Nh-haze: An image dehazing benchmark with non- homogeneous hazy and haze-free images","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.762119Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:a5bb2b604d6a5e1c619658c28f34335ba8eaf83ffc4ae834f1cb74d9d1a5fb7f","observation_id":"5473f44b-3596-4e58-befa-08a6bc11bab0","resolution":{"observed_at":"2026-08-15T19:21:34.762119Z","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":"2026-08-15T19:21:34.765790Z","title":"Contour detection and hierarchical image segmentation.IEEE transactions on pattern analysis and machine intelligence, 33(5):898–916, 2010","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.765790Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:4776f4daa38d2b1c0c05c7f7b44b242485fe116c825d76f9ecd003d1bba4605b","observation_id":"16da9acf-fa7b-4849-87c3-d5fd7811ccba","resolution":{"observed_at":"2026-08-15T19:21:34.765790Z","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":"2026-08-15T19:21:34.769489Z","title":"Wasserstein generative adversarial networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.769489Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:1b501ad6235eb148dd7007708e0b8f735bb2760a49772219477704b62aebbc40","observation_id":"6f4cd16a-1f2f-45e4-bcab-197f5bc15c51","resolution":{"observed_at":"2026-08-15T19:21:34.769489Z","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":"2026-08-15T19:21:34.773061Z","title":"Self-guided image dehazing using progressive feature fu- sion.IEEE Transactions on Image Processing, 31:1217– 1229, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.773061Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:ec75bb0cfad2a46b44d8f496c11009fbe1c53b35c88d1c5eedb8701a3e21ceaf","observation_id":"83ddb01a-01ad-40a5-b9e7-bdf11d3a9950","resolution":{"observed_at":"2026-08-15T19:21:34.773061Z","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":"2026-08-15T19:21:34.776957Z","title":"Digital image restoration.IEEE signal processing magazine, 14(2):24– 41, 1997","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.776957Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:0e1e3b8808b1df30a0d536a3365556db35704bbb90c5f039e723a1934c812792","observation_id":"14f501ee-c689-4a1d-9bdd-8f6337de72b2","resolution":{"observed_at":"2026-08-15T19:21:34.776957Z","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":"2026-08-15T19:21:34.780278Z","title":"Cold diffusion: Inverting arbitrary im- age transforms without noise.Advances in Neural Informa- tion Processing Systems, 36:41259–41282, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.780278Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:c4c274abf12fbf775bf90eb7dc26faff3ca0899c66bc2d4d9b297896357d6c65","observation_id":"707b23b0-96a1-44eb-874e-67d150dc43e0","resolution":{"observed_at":"2026-08-15T19:21:34.780278Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1107.0740","last_updated":"2012-09-04T16:43:48Z","snapshot_observed_at":"2026-08-16T12:44:00.939563Z","submitted_at":"2011-07-04T20:34:23Z","title":"An intuitive proof of the data processing inequality","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1107.0740","snapshot_observed_at":"2026-08-15T19:21:34.783284Z","title":"An intuitive proof of the data processing inequality.arXiv preprint arXiv:1107.0740, 2011","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.783284Z"},"links":{"cited_paper":"/paper/1107.0740","citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:7fb4bafadbbb515b548929bcdc6fd170bbb66d412ce8aa17300738cbbe748d97","observation_id":"6829ce68-eabb-4acf-b73e-fd0b193d2474","resolution":{"observed_at":"2026-08-15T19:21:34.783284Z","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":"2026-08-15T19:21:34.786792Z","title":"The perception-distortion tradeoff","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.786792Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:c585e70dcfad73f694a1555e3cfec4faf793f9ee0b3a1ff3a56760485facdf96","observation_id":"609cfcc2-6f54-4155-8dfd-60839a2dad5e","resolution":{"observed_at":"2026-08-15T19:21:34.786792Z","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":"2026-08-15T19:21:34.789719Z","title":"Dehazenet: An end-to-end system for single image haze removal.IEEE transactions on image process- ing, 25(11):5187–5198, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.789719Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:be775bd936af655c9de8dd743ee8ad52c3ebbb877521540de4eb86540a86fcb9","observation_id":"cfbf2cb0-1687-45b8-a391-44561e1d78f0","resolution":{"observed_at":"2026-08-15T19:21:34.789719Z","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":"2026-08-15T19:21:34.792648Z","title":"Simple baselines for image restoration","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.792648Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:9a553904af7cace9fc3c558ea34225d45c48f113afeb4000e941a3ee179c26b6","observation_id":"26a00edb-41c3-42af-a38f-7f4c01b4ad27","resolution":{"observed_at":"2026-08-15T19:21:34.792648Z","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":"2026-08-15T19:21:34.795437Z","title":"Neural ordinary differential equa- tions.Advances in neural information processing systems, 31, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.795437Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:e2afb1a2d5439f9a2c0a4e5c333227eaa629cf8d97635dc5a1f092affe79c02a","observation_id":"257a7c13-5d3b-4aa5-b0e7-dd9a77ea8b9a","resolution":{"observed_at":"2026-08-15T19:21:34.795437Z","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":"2026-08-15T19:21:34.798619Z","title":"Jstasr: Joint size and transparency- aware snow removal algorithm based on modified par- tial convolution and veiling effect removal","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.798619Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:dbd19a916a433a1742b4b07826e8d71bab1c90044b9cb841d3c91c9a0750989f","observation_id":"d4d6ecba-1a2e-49be-a675-acfc68f016c5","resolution":{"observed_at":"2026-08-15T19:21:34.798619Z","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":"2026-08-15T19:21:34.801473Z","title":"Learning a sparse transformer network for effective image deraining","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.801473Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:e8a5408681efb2587e38adf3822b9f3de47790739ecb18f22cf33832c6c7b290","observation_id":"5e9038f6-242d-4420-bf03-1590f9438038","resolution":{"observed_at":"2026-08-15T19:21:34.801473Z","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":"2026-08-15T19:21:34.804638Z","title":"Rethinking coarse-to-fine ap- proach in single image deblurring","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.804638Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:8511e072b65b4f584b219c1b43d025c27a976805820e01fa48c351b830c6e19d","observation_id":"e5731d3e-1147-4749-b7df-a743281189f5","resolution":{"observed_at":"2026-08-15T19:21:34.804638Z","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":"2026-08-15T19:21:34.807717Z","title":"Focal network for image restoration","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.807717Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:aab61693059a6ed44d2e92db4a1e11e89e1ff7faf564bc324d04992596bc9429","observation_id":"9c7bb32f-06c1-4479-ac45-fe2e91000d3e","resolution":{"observed_at":"2026-08-15T19:21:34.807717Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.11435","last_updated":"2024-02-02T18:52:51Z","snapshot_observed_at":"2026-08-21T11:19:26.795136Z","submitted_at":"2023-03-20T20:28:17Z","title":"Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.11435","snapshot_observed_at":"2026-08-15T19:21:34.810469Z","title":"Inversion by di- rect iteration: An alternative to denoising diffusion for im- age restoration.arXiv preprint arXiv:2303.11435, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.810469Z"},"links":{"cited_paper":"/paper/2303.11435","citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:2ccf799e0e3a4bdd8487f8629f4675e10fa526d24bc59804dfb440fb295c3337","observation_id":"374dc04f-0554-4d44-ac9e-47fcd78f48c8","resolution":{"observed_at":"2026-08-15T19:21:34.810469Z","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":"2026-08-15T19:21:34.814122Z","title":"Detail- recovery image deraining via context aggregation networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.814122Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:aa50fa0800241fcc23cf729e08499f1004460e79cbbff15d09f745927eec02b9","observation_id":"c902da1e-9c72-4da3-9ef2-6d638c1cdcae","resolution":{"observed_at":"2026-08-15T19:21:34.814122Z","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":"2026-08-15T19:21:34.817663Z","title":"Multi-scale boosted de- hazing network with dense feature fusion","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.817663Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:c48abc42ab536f9d964b61b20838f51e7d316924648876df1357501227b518bd","observation_id":"a20454e7-f896-475e-ac3f-b1f9aac39cf4","resolution":{"observed_at":"2026-08-15T19:21:34.817663Z","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":"2026-08-15T19:21:34.821288Z","title":"Quantization guided jpeg artifact correction","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.821288Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:36380fd075f0be029d8005fe160e812168b7d2594b3f1a6e99b394829a81adff","observation_id":"7e48c6aa-05f8-443a-9c1e-32f6985cb937","resolution":{"observed_at":"2026-08-15T19:21:34.821288Z","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":"2026-08-15T19:21:34.824762Z","title":"Gener- ative diffusion prior for unified image restoration and en- hancement","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.824762Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:96e260ef052c07f80257bfd82698cbe31381593d98c05ceb11e81b7ad01bf1ce","observation_id":"8c7db254-1f34-4027-aac3-e7848441a68a","resolution":{"observed_at":"2026-08-15T19:21:34.824762Z","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":"2026-08-15T19:21:34.828306Z","title":"Generative adversarial networks.Com- munications of the ACM, 63(11):139–144, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.828306Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:c58d3538130368ad474c14e4896e28a3b8c05500b889211070a7c5ddaf14cd85","observation_id":"4b8e5b94-eeb1-4aa5-a874-4a3267226490","resolution":{"observed_at":"2026-08-15T19:21:34.828306Z","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":"2026-08-15T19:21:34.831804Z","title":"Improved training of wasserstein gans.Advances in neural information process- ing systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.831804Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:4b3d68f90adf2993f77a84c823d53023ae7590050c3f67a20f7b11f3ac91c4c1","observation_id":"8503b367-310d-422b-9811-fa7595d50c35","resolution":{"observed_at":"2026-08-15T19:21:34.831804Z","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":"2026-08-15T19:21:34.835860Z","title":"Image dehazing transformer with transmission-aware 3d position embedding","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.835860Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:edc2a6e8a2c54b82563bca0c5577f208c1246d9c759979719ff67b043f92ca11","observation_id":"3165ef69-2701-421e-803d-097dd4bc820e","resolution":{"observed_at":"2026-08-15T19:21:34.835860Z","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":"2026-08-15T19:21:34.839375Z","title":"From sky to the ground: A large-scale bench- mark and simple baseline towards real rain removal","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.839375Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:c6a0d0e779bf1b19e05d9e5ca0ac9ceed71055e7220757ca9fd351218ac36e5e","observation_id":"2d7aac2c-4b00-4a2e-9eaa-47f0e232d9a7","resolution":{"observed_at":"2026-08-15T19:21:34.839375Z","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":"2026-08-15T19:21:34.842744Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.842744Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:de41fc8e0b6e42dcff106c3abb90520522abe47fd2be7f1018e09799e848569f","observation_id":"c6b74435-1eb8-4d96-b7e8-525c39cc3bfd","resolution":{"observed_at":"2026-08-15T19:21:34.842744Z","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":"2026-08-15T19:21:34.846030Z","title":"Generic image restoration with flow based priors","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.846030Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:d83e8a2ce9a7c7a9cc7ff15aa784ac4b7c528b7153fab45b0e027b91e2e5280d","observation_id":"e7913b69-e2ed-4cc2-be69-3dc39fd2550a","resolution":{"observed_at":"2026-08-15T19:21:34.846030Z","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":"2026-08-15T19:21:34.849679Z","title":"Denoising dif- fusion probabilistic models.Advances in neural informa- tion processing systems, 33:6840–6851, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.849679Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:c1362a9d1fa7d8cb057034b85d8c6f6f45004aac3808cfa391d7313ab0bcffe3","observation_id":"d12a0458-6611-4b9e-8b05-fa6dda9dd29c","resolution":{"observed_at":"2026-08-15T19:21:34.849679Z","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":"2026-08-15T19:21:34.853208Z","title":"Selective wavelet attention learning for single im- age deraining.International Journal of Computer Vision, 129(4):1282–1300, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.853208Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:00015a6146437030f7d167ceb957ee6135c967cd7a9ff9361ff6c09478d4da5a","observation_id":"9c97c0f9-ccb1-4865-a44f-7cab6c78ac07","resolution":{"observed_at":"2026-08-15T19:21:34.853208Z","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":"2026-08-15T19:21:34.856626Z","title":"Arbitrary style transfer in real-time with adaptive instance normalization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.856626Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:87abd8a20ab61ce097af062e4661c66a5fccf60ddabbd76aad19386675114ac1","observation_id":"420953c7-c4cb-4149-ab18-fa852e755e3b","resolution":{"observed_at":"2026-08-15T19:21:34.856626Z","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":"2026-08-15T19:21:34.860043Z","title":"Image-to-image translation with conditional adver- sarial networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.860043Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:fe5e81f2d898ac44b29438d0fefabe405948086c12e0f2436ab5c657254bb3d6","observation_id":"7dfadaa9-ba84-462d-b20a-95bb18b91526","resolution":{"observed_at":"2026-08-15T19:21:34.860043Z","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":"2026-08-15T19:21:34.863965Z","title":"Towards flex- ible blind jpeg artifacts removal","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.863965Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:003e7db0bc95290276d3d6828aa55b8c2f9c059e9314c3b5554158ccf4cd9ddb","observation_id":"ec714f9d-10ef-4c25-8fee-2338e94a2703","resolution":{"observed_at":"2026-08-15T19:21:34.863965Z","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":"2026-08-15T19:21:34.867701Z","title":"Rain- free and residue hand-in-hand: A progressive coupled net- work for real-time image deraining.IEEE Transactions on Image Processing, 30:7404–7418, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.867701Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:e2571df50218c06504a2a1ccc3195722d74944f56d40e7799dda358c80a2d85e","observation_id":"00137470-73ac-43de-a5e9-45cd2469dae1","resolution":{"observed_at":"2026-08-15T19:21:34.867701Z","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":"2026-08-15T19:21:34.871321Z","title":"Edge-based defocus blur estimation with adaptive scale selection.IEEE Trans- actions on Image Processing, 27(3):1126–1137, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.871321Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:8183aa3455aa139a70fcf1bdace41830164c5cf5b8bc9991c5e2e89e70dcd223","observation_id":"5fcbf42b-55ec-402d-99f1-877d4294d680","resolution":{"observed_at":"2026-08-15T19:21:34.871321Z","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":"2026-08-15T19:21:34.874738Z","title":"Denoising diffusion restoration models.Advances in Neural Information Processing Systems, 35:23593–23606,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.874738Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:50f808d642ec0541719b29dfecc28e21872b2f718433a2abb086b8ae38231c43","observation_id":"3e9aa577-52ce-4280-be1f-eebe7f3791cd","resolution":{"observed_at":"2026-08-15T19:21:34.874738Z","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":"2026-08-15T19:21:34.878599Z","title":"Bigcolor: Colorization using a genera- tive color prior for natural images","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.878599Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:7656ac04d7c00dd5d8e33255fc27621037c17e1b0cfc7b4fed0ca2c6ffa332d1","observation_id":"5ec684db-e507-4f57-9fdb-18fbbdcfa75d","resolution":{"observed_at":"2026-08-15T19:21:34.878599Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6114","last_updated":"2022-12-10T21:04:00Z","snapshot_observed_at":"2026-08-14T23:50:45.029465Z","submitted_at":"2013-12-20T20:58:10Z","title":"Auto-Encoding Variational Bayes","version":11},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6114","snapshot_observed_at":"2026-08-15T19:21:34.882205Z","title":"Auto-encoding variational bayes","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.882205Z"},"links":{"cited_paper":"/paper/1312.6114","citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:e362a7bce75d12137f7bea6ddc5d108911ec14c77bb828dad077fa10be72fe46","observation_id":"5db454cc-d156-4f40-a4b6-9f7b2a3a7ba6","resolution":{"observed_at":"2026-08-15T19:21:34.882205Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-17T19:26:44.032537Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-15T19:21:34.885867Z","title":"Adam: A method for stochastic opti- mization.arXiv preprint arXiv:1412.6980, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.885867Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:9b3850ee7d08073aaf9e903f6b70d75666d6e518b06c7a955f4ced593b5a857e","observation_id":"b293fc53-bb6b-4ce1-8ade-247d137233ea","resolution":{"observed_at":"2026-08-15T19:21:34.885867Z","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":"2026-08-15T19:21:34.889491Z","title":"Glow: Generative flow with invertible 1x1 convolutions.Advances in neural information processing systems, 31, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.889491Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:63c0550ed0e5b2ac30c34c3580cbf03b60434c58632e880d0b9a83896dcb57e6","observation_id":"b760ff1f-5254-4798-bcd7-9aa57fe8b082","resolution":{"observed_at":"2026-08-15T19:21:34.889491Z","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":"2026-08-15T19:21:34.893835Z","title":"Estimating mutual information.Physical Review E—Statistical, Nonlinear, and Soft Matter Physics, 69(6): 066138, 2004","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.893835Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:a35b62d7dea28f5a5bf0bc36eaa746701f62c8dd9f5c2135cef3367dd5eee335","observation_id":"7694d340-7de1-4134-abf6-5961ba1f8179","resolution":{"observed_at":"2026-08-15T19:21:34.893835Z","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":"2026-08-15T19:21:34.897303Z","title":"Photo-realistic single image super-resolution using a gener- ative adversarial network","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.897303Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:3ae25404bde765e03aaa610c2a7df66a5c996c992af1be8e21660f5f06c9b388","observation_id":"60cf6269-f485-43ca-89e8-542127982b99","resolution":{"observed_at":"2026-08-15T19:21:34.897303Z","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":"2026-08-15T19:21:34.900893Z","title":"Deep defocus map estimation using domain adapta- tion","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.900893Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:6bc09e3abf96354a031a702c920ae135353e04694bc562a5958ffd663016eb79","observation_id":"6f78f245-23a7-4b28-bc48-dc6244200b8b","resolution":{"observed_at":"2026-08-15T19:21:34.900893Z","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":"2026-08-15T19:21:34.904567Z","title":"Iterative filter adaptive network for single image defocus deblurring","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.904567Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:068829b8e36138063d9f6171733eb0b8486b1e105ac3fee7ac642be3ce52fc8c","observation_id":"12a29aa7-14ac-4675-ac14-0bd29f92d58e","resolution":{"observed_at":"2026-08-15T19:21:34.904567Z","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":"2026-08-15T19:21:34.907996Z","title":"Aod-net: All-in-one dehazing network","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.907996Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:5640debe1b29a2fc05ada6cd99bf0bb6475e4aca91ab85ed4e1ac4fb59a4dd7d","observation_id":"482766fb-10cc-4c85-a5b9-235d444e8d99","resolution":{"observed_at":"2026-08-15T19:21:34.907996Z","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":"2026-08-15T19:21:34.911337Z","title":"Srdiff: Single image super-resolution with diffusion probabilistic models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.911337Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:9d9265bcd82bb6d9c07f101378df941fc1b8cf97c3d730c135b82eed8afacc77","observation_id":"73f294ac-7045-430d-b05b-44a1cf34ba0e","resolution":{"observed_at":"2026-08-15T19:21:34.911337Z","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":"2026-08-15T19:21:34.914558Z","title":"Heavy rain image restoration: Integrating physics model and conditional adversarial learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.914558Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:429df50b7090d0bb11980de5cd81e208af29ad888ec28ecbb78e60d271e346cb","observation_id":"1fa58c86-9cef-421f-a939-cd02cf9e08b4","resolution":{"observed_at":"2026-08-15T19:21:34.914558Z","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":"2026-08-15T19:21:34.918069Z","title":"Recurrent squeeze-and-excitation context aggre- gation net for single image deraining","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.918069Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:d674445e875b903e4dd806b2e54e8a71ec96b1df4720e319ca03874c9a81c8ea","observation_id":"988ac89a-24c9-4859-be8c-6a32720674aa","resolution":{"observed_at":"2026-08-15T19:21:34.918069Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.15070","last_updated":"2024-04-12T05:26:59Z","snapshot_observed_at":"2026-08-16T15:05:03.053812Z","submitted_at":"2023-08-29T07:11:52Z","title":"DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.15070","snapshot_observed_at":"2026-08-15T19:21:34.921735Z","title":"Diffbir: Towards blind image restoration with generative diffusion prior.arXiv preprint arXiv:2308.15070, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.921735Z"},"links":{"cited_paper":"/paper/2308.15070","citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:6fad866483972446c9c730fd46664bf61c65e817bf810ccce76ac9827aa6dbcb","observation_id":"714251e1-ff08-49c9-a45d-b9a33b21bb92","resolution":{"observed_at":"2026-08-15T19:21:34.921735Z","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":"2026-08-15T19:21:34.924737Z","title":"Catch missing details: Image reconstruction with frequency augmented variational autoencoder","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.924737Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:6c4ab8f88857535d9574226b03ab04acf81dc675f0a2c26decf87cb6dc6f3f8b","observation_id":"98b97269-a066-4c13-a6bd-65f0a76378c3","resolution":{"observed_at":"2026-08-15T19:21:34.924737Z","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":"2026-08-15T19:21:34.927630Z","title":"Unsupervised image denoising in real-world scenarios via self-collaboration parallel generative adversarial branches","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.927630Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:7c46a82100e805e00a7bf6a3c49dcaba07433f7dcd42a36c0928bcc6df001fc4","observation_id":"f92508da-9d80-42d2-a0ad-1a1edbba755f","resolution":{"observed_at":"2026-08-15T19:21:34.927630Z","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":"2026-08-15T19:21:34.930769Z","title":"Flow matching for generative modeling.arXiv preprint arXiv:2210.02747, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.930769Z"},"links":{"cited_paper":"/paper/2210.02747","citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:90516b6a448b670fb57dc589ff262558ebb13f9d5cfd78608fbd35bf7d6f58f5","observation_id":"2d1267ab-3cda-4e17-8a3b-a27f7222905d","resolution":{"observed_at":"2026-08-15T19:21:34.930769Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.05872","last_updated":"2023-05-26T02:55:08Z","snapshot_observed_at":"2026-08-16T15:55:59.111718Z","submitted_at":"2023-02-12T08:35:39Z","title":"I$^2$SB: Image-to-Image Schr\\\"odinger Bridge","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.05872","snapshot_observed_at":"2026-08-15T19:21:34.933943Z","title":"I2sb: Image-to-image schr ¨odinger bridge.arXiv preprint arXiv:2302.05872, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.933943Z"},"links":{"cited_paper":"/paper/2302.05872","citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:3221ca2ce20934c4f4bd8e66a316a7385747e22dedcb47455cc5a377e5ecbc45","observation_id":"f7a6f932-e1ff-4f44-9754-0409f8e6e0c3","resolution":{"observed_at":"2026-08-15T19:21:34.933943Z","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":"2026-08-15T19:21:34.937287Z","title":"Structure matters: Tackling the semantic dis- crepancy in diffusion models for image inpainting","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.937287Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:cdbf5061b00b7a7f61b6dc57d77c794097451424114d7d76f6f31ba8bb012179","observation_id":"6e9d04dc-3f89-426f-8ffa-424b4a20352c","resolution":{"observed_at":"2026-08-15T19:21:34.937287Z","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":"2026-08-15T19:21:34.940119Z","title":"Residual denoising diffu- sion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.940119Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:d633eccc45ae290401bdeda1a2a4d5175c917e2413ec664dbdebccec2e7783d5","observation_id":"b816b116-818d-4453-bd1a-78a3addbfb2b","resolution":{"observed_at":"2026-08-15T19:21:34.940119Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.03003","last_updated":"2022-09-07T08:59:55Z","snapshot_observed_at":"2026-07-06T13:49:40.974495Z","submitted_at":"2022-09-07T08:59:55Z","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.03003","snapshot_observed_at":"2026-08-15T19:21:34.943657Z","title":"Flow straight and fast: Learning to generate and transfer data with rectified flow.arXiv preprint arXiv:2209.03003, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.943657Z"},"links":{"cited_paper":"/paper/2209.03003","citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:d27f1ec2a9ec5ba6c5a10be6b0bbe8a7d556e6f2ba5b80b9fd0d14160f6b7db0","observation_id":"43fc821a-8be2-45c1-8d32-4c98052f91cc","resolution":{"observed_at":"2026-08-15T19:21:34.943657Z","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":"2026-08-15T19:21:34.947793Z","title":"Diff-plugin: Revitalizing details for diffusion-based low-level tasks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.947793Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:5fc217a9bacbd65c16f176845dd37775148733c4cca2a1ab75629bed95e02464","observation_id":"a4ce1e03-ed3f-4fa1-8a1f-cec1b179bf21","resolution":{"observed_at":"2026-08-15T19:21:34.947793Z","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":"2026-08-15T19:21:34.951452Z","title":"Desnownet: Context-aware deep network for snow removal.IEEE Transactions on Image Processing, 27(6): 3064–3073, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.951452Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:9584eab3b1bc99ab9bb0afc62644e7bdd49b058234d4bb51be81f096f51126dd","observation_id":"53d9c5f6-430c-4c68-8833-100e8ce28352","resolution":{"observed_at":"2026-08-15T19:21:34.951452Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-14T20:13:52.872565Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-15T19:21:34.955293Z","title":"Decoupled weight decay regularization.arXiv preprint arXiv:1711.05101, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.955293Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:2b32463edc413d1c98cd15357073daa78c791a2d240c3fb40df3d8778e7fe6da","observation_id":"950e79ac-357a-4e74-942c-234fa814d567","resolution":{"observed_at":"2026-08-15T19:21:34.955293Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1608.03983","last_updated":"2017-05-03T16:28:09Z","snapshot_observed_at":"2026-07-06T05:06:55.589962Z","submitted_at":"2016-08-13T13:46:05Z","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.03983","snapshot_observed_at":"2026-08-15T19:21:34.958879Z","title":"Sgdr: Stochastic gradient descent with warm restarts.arXiv preprint arXiv:1608.03983, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.958879Z"},"links":{"cited_paper":"/paper/1608.03983","citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:20328fbd751cee84122f10b11c497ee23faca0b194c82fea521000bd08239a48","observation_id":"f0c6acf0-bf59-4424-be36-08c676251027","resolution":{"observed_at":"2026-08-15T19:21:34.958879Z","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":"2026-08-15T19:21:34.962464Z","title":"Normalizing flow as a flexi- ble fidelity objective for photo-realistic super-resolution","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.962464Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:7cc5a057fa71013af93ef43c05b2b320e746a7e47eeb7fb2a3ae597d25453452","observation_id":"e5fa4044-f698-483c-9d5e-4b73e741eb82","resolution":{"observed_at":"2026-08-15T19:21:34.962464Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.11699","last_updated":"2023-05-31T12:41:58Z","snapshot_observed_at":"2026-08-16T15:59:43.691036Z","submitted_at":"2023-01-27T13:20:48Z","title":"Image Restoration with Mean-Reverting Stochastic Differential Equations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.11699","snapshot_observed_at":"2026-08-15T19:21:34.966036Z","title":"Image restoration with mean-reverting stochastic differential equations.arXiv preprint arXiv:2301.11699, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.966036Z"},"links":{"cited_paper":"/paper/2301.11699","citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:29ab7a586381bf5b395d3114f2a20cbaa2179a9155d813dafb6818152ea8bfd8","observation_id":"71d8a9f6-3666-4e7d-a0ca-0138bb7b5f75","resolution":{"observed_at":"2026-08-15T19:21:34.966036Z","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":"2026-08-15T19:21:34.969655Z","title":"Refusion: Enabling large- size realistic image restoration with latent-space diffusion models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.969655Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:b9cabaee56ef56bcc94694fa010d750fa1bee66b09afbe024bf739552da687b8","observation_id":"28ea34ae-2eb3-4ca8-8afc-cb7e9ff45c70","resolution":{"observed_at":"2026-08-15T19:21:34.969655Z","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":"2026-08-15T19:21:34.973571Z","title":"Sen- sitivity decouple learning for image compression artifacts reduction.IEEE Transactions on Image Processing, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.973571Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:765df1367a1af18721707f478c87452a587164ded95093c3d0aa1873310d79a6","observation_id":"5e6e4153-9f22-42eb-823b-51c08283ea2b","resolution":{"observed_at":"2026-08-15T19:21:34.973571Z","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":"2026-08-15T19:21:36.182178Z","title":"Least squares gen- erative adversarial networks","venue":null,"work_id":"08d05d73-5cf8-4184-96b3-7ec7e7d74e9d","year":2017},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.977282Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:a96c16a5c14680242b9ea48409af26965c645c017a604bf10aadda4e465578a2","observation_id":"943e7e9d-4368-4b4b-a665-db49132ede5e","resolution":{"observed_at":"2026-08-15T19:21:36.185825Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.11745","last_updated":"2022-11-29T10:15:57Z","snapshot_observed_at":"2026-08-16T17:39:58.799655Z","submitted_at":"2021-11-23T09:40:40Z","title":"Intriguing Findings of Frequency Selection for Image Deblurring","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.11745","snapshot_observed_at":"2026-08-15T19:21:34.980731Z","title":"Deep residual fourier transformation for single im- age deblurring.arXiv preprint arXiv:2111.11745, 2(3):5,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.980731Z"},"links":{"cited_paper":"/paper/2111.11745","citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:b09f2ccae7bc07900296939e25372ab38fe828e9c5e5f47a13f8f25e20152c56","observation_id":"87f900d8-3c9d-40d8-adb5-23f3d342f6b8","resolution":{"observed_at":"2026-08-15T19:21:34.980731Z","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":"2026-08-15T19:21:36.171444Z","title":"A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics","venue":null,"work_id":"1d52ee5c-f28f-4ca4-96a5-ac7ef298dc36","year":2001},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.984634Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:5f961f709e9d1ce55ddb4c3bc6782ea522cf87121998da0df9fb06451dc27f0c","observation_id":"8b6a82b7-91ae-4260-930c-28cd8b62e7e5","resolution":{"observed_at":"2026-08-15T19:21:36.175347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1411.1784","last_updated":"2014-11-06T22:33:22Z","snapshot_observed_at":"2026-08-16T19:10:09.657437Z","submitted_at":"2014-11-06T22:33:22Z","title":"Conditional Generative Adversarial Nets","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1411.1784","snapshot_observed_at":"2026-08-15T19:21:34.988263Z","title":"Conditional generative adversarial nets","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.988263Z"},"links":{"cited_paper":"/paper/1411.1784","citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:0e5052265f95d008879e37673288ebc0073d17e0495430708e4eded67fa98f27","observation_id":"ae3becce-eb35-4ac9-98e1-dceff4aae8e5","resolution":{"observed_at":"2026-08-15T19:21:34.988263Z","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":"2026-08-15T19:21:36.160382Z","title":"Noisier2noise: Learning to denoise from unpaired noisy data","venue":null,"work_id":"690f834e-6dc3-4073-acdf-7503c22e5eae","year":null},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.992122Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:ea24a81f74d595fd12f18d58d5e8acfebfb1a61ee33b3f5ab295a3ef7a14964f","observation_id":"57340eac-343a-43f8-8c7a-60aeefb5b29e","resolution":{"observed_at":"2026-08-15T19:21:36.164179Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T19:21:36.149300Z","title":"Dynamic at- tentive graph learning for image restoration","venue":null,"work_id":"e0edd196-1e80-47da-ac87-e276be2bd074","year":2021},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.995711Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:509947104ef84194ccfe86575dc58b37f63b69be50fc1a4b1a4c3b9ae45102e3","observation_id":"a6545c56-86d9-4e8f-a001-32286d102ec3","resolution":{"observed_at":"2026-08-15T19:21:36.153036Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T19:21:36.138277Z","title":"T2i-adapter: Learn- ing adapters to dig out more controllable ability for text-to- image diffusion models","venue":null,"work_id":"b81d5a04-38a5-4dba-a162-ebcd20e508e7","year":2024},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:34.999398Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:d01163314c4c1134754458289f82c7b31500e702f4b59fbf021412a7b3e04cc7","observation_id":"989077ea-9283-448c-8c9e-831e07aa4189","resolution":{"observed_at":"2026-08-15T19:21:36.142231Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.12831","last_updated":"2023-02-14T15:13:33Z","snapshot_observed_at":"2026-08-21T08:31:58.757706Z","submitted_at":"2023-02-14T15:13:33Z","title":"CDPMSR: Conditional Diffusion Probabilistic Models for Single Image Super-Resolution","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.12831","snapshot_observed_at":"2026-08-15T19:21:35.003025Z","title":"Cdpmsr: Condi- tional diffusion probabilistic models for single image super- resolution.arXiv preprint arXiv:2302.12831, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.003025Z"},"links":{"cited_paper":"/paper/2302.12831","citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:e5a323c945c2ca915dba097c14deaedbd6f2e9c4b2d8443fb95617c68536e476","observation_id":"4b0babe8-709a-4f85-b257-8ee2e668cb8b","resolution":{"observed_at":"2026-08-15T19:21:35.003025Z","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":"2026-08-15T19:21:36.126935Z","title":"Ot-flow: Fast and accurate continuous normal- izing flows via optimal transport","venue":null,"work_id":"b71b8ea0-113a-4f48-a379-3376cb5463e0","year":2021},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.007119Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:473b710ac0c5fd97d42382d262dc8da85abfec855907bcc48d7dc360aa9db7b3","observation_id":"c0397dff-2d25-4412-95d1-43d1c7c30784","resolution":{"observed_at":"2026-08-15T19:21:36.131073Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T19:21:36.116102Z","title":"Restoring vision in adverse weather conditions with patch-based denoising diffusion models.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(8):10346–10357, 2023","venue":null,"work_id":"fae0e0d8-b529-413c-bba8-c623248c8776","year":2023},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.010688Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:374ddd365294b7a8ea1c1bdf02e23b3d39b6cd05469558765be727d778feb0f6","observation_id":"b4bec076-f946-4952-8056-d449636854e2","resolution":{"observed_at":"2026-08-15T19:21:36.119412Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T19:21:36.107030Z","title":"Exploiting deep genera- tive prior for versatile image restoration and manipulation","venue":null,"work_id":"5a42633d-b368-461f-88b5-bbfd6994f832","year":2021},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.014264Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:995aabc7cf52ce2b3eed64019f1548d092e3a18b41d433d6a958e983fc44c4ca","observation_id":"8962cb72-3401-4d33-94de-6be22f6260e8","resolution":{"observed_at":"2026-08-15T19:21:36.109981Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T19:21:36.097175Z","title":"Normalizing flows for probabilistic modeling and infer- ence.Journal of Machine Learning Research, 22(57):1–64,","venue":null,"work_id":"513508e7-ae48-4d34-8c8d-e1148a81e7d0","year":null},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.017749Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:f7b90781c09fd90b717256021a35bb5fbd0622774dad97d160eaeb207347bbf2","observation_id":"ebaa231c-973c-4cf8-aec2-b6a6f9518076","resolution":{"observed_at":"2026-08-15T19:21:36.100197Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T19:21:36.087152Z","title":"Ffa-net: Feature fusion attention network for single image dehazing","venue":null,"work_id":"d0df1655-afa2-4eb8-bd34-918ff21563fe","year":2020},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.021246Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:17ca474d48f32a3b163792895271dacd3ea22f15a1e852787d4f3f5e94618629","observation_id":"3562fe91-862f-485c-997b-ee848f068f11","resolution":{"observed_at":"2026-08-15T19:21:36.090516Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T19:21:36.075720Z","title":"Mb-taylorformer: Multi-branch efficient transformer expanded by taylor formula for im- age dehazing","venue":null,"work_id":"42c2735a-6389-44f1-bcf2-cf12d90db22a","year":2023},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.024860Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:80ae6052f200d97a8648a35337d31aa29bbe0aa6052f255456164035008ae46b","observation_id":"525f8c8a-c7df-4fee-b9b5-21eaa7bab082","resolution":{"observed_at":"2026-08-15T19:21:36.079768Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T19:21:35.028618Z","title":"Adaptive consistency prior based deep network for image denoising","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.028618Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:2b57b8cbeeb9b5c771cacc1b74194155af3b9647cf37781aa1b7e194ec374aeb","observation_id":"e8f29925-d96e-473a-9085-7e240ad09021","resolution":{"observed_at":"2026-08-15T19:21:35.028618Z","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":"2026-08-15T19:21:36.057721Z","title":"Progressive image deraining net- works: A better and simpler baseline","venue":null,"work_id":"08d83797-be73-4c80-b647-6bb2f989677d","year":2019},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.032143Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:c9e454a4193e963f08685a0e8786d5a36f6c0a6b268f86fa18f11518fe89e909","observation_id":"b1103532-9f10-4f24-b325-31892d2c4a92","resolution":{"observed_at":"2026-08-15T19:21:36.061598Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T19:21:35.035853Z","title":"U- net: Convolutional networks for biomedical image segmen- tation","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.035853Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:e29b69c9d62eaa12b07cab0a4137075a3fd41cf640319a6f45190195dc18df15","observation_id":"12bbe418-b832-48c4-b670-9815aa6172aa","resolution":{"observed_at":"2026-08-15T19:21:35.035853Z","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":"2026-08-15T19:21:36.038158Z","title":"Learning to deblur using light field generated and real de- focus images","venue":null,"work_id":"c6c6f791-f92d-4062-9fa6-cf5fc91b2a7e","year":2022},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.038863Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:46763626bc258ef8ed7409689b3516ac5dc7f9a235b236d6deadadfe100b3684","observation_id":"1252388f-02c7-4956-a2a3-000ee657856c","resolution":{"observed_at":"2026-08-15T19:21:36.041958Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T19:21:36.026184Z","title":"Improved techniques for training gans.Advances in neural information process- ing systems, 29, 2016","venue":null,"work_id":"058b71b5-943d-4233-9f9f-ba6477a78d66","year":2016},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.041729Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:0199620e0ca931e80103fa6470acdd2e3ab6f4a4ef10df74def52ee36b3d2d19","observation_id":"bfc50c6c-dbbf-4555-9a7d-0641b315e732","resolution":{"observed_at":"2026-08-15T19:21:36.030267Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T19:21:36.014659Z","title":"Resdiff: Combining cnn and diffusion model for image super-resolution","venue":null,"work_id":"7ce6e46b-8192-41ed-a96a-3a6347f59be2","year":2024},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.044723Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:d2e2a1ae044d1a5781b9a58621d55431d9e70ece533e5de2c57a3e851ed43c11","observation_id":"7b69af0c-ac78-4690-b0fe-13e7cd85f894","resolution":{"observed_at":"2026-08-15T19:21:36.018313Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T19:21:36.002993Z","title":"Live image quality assessment database release 2.http://live","venue":null,"work_id":"5aa295fb-4f5b-4590-838f-edfdc8512246","year":2005},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.047617Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:7963f13c220346f0fcf0f6064531cc42759c071d4dbcee744ed966f877b6b1e1","observation_id":"bd6116dc-7c66-417e-83a6-88e5644ad560","resolution":{"observed_at":"2026-08-15T19:21:36.007402Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T19:21:35.873767Z","title":"Just noticeable defocus blur detection and estimation","venue":null,"work_id":"bfaf2c8d-acbe-46eb-9cea-43124ebc5347","year":2015},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.050630Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:dd3441bd704c06ca6f14c07ac40d081336c8cdbae0ec9add42a0054d7579754c","observation_id":"161da953-d15a-4dcc-b305-62318e6716e8","resolution":{"observed_at":"2026-08-15T19:21:35.877558Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T19:21:35.862373Z","title":"Resfusion: Denoising diffusion probabilistic models for image restoration based on prior residual noise","venue":null,"work_id":"b53340a5-e871-445e-8e29-551338010d08","year":2023},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.053674Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:5a09e0cbf358afd1a8cee36876fc06f2118e64780227d9503703d2922da2c50e","observation_id":"1e905423-7b60-4474-892e-9c7e3f2f4702","resolution":{"observed_at":"2026-08-15T19:21:35.866549Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T19:21:35.852079Z","title":"Variational deep image restoration.IEEE Transactions on Image Processing, 31: 4363–4376, 2022","venue":null,"work_id":"e35421e2-b971-418c-9fef-c80e18cccee0","year":2022},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.056571Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:79fa0c508023062c1fcc4c7e02cd91c98e7bdc41dd0b9c49818fdf4b828c3d74","observation_id":"d402ebb7-345a-47ae-99f8-ee474e84e086","resolution":{"observed_at":"2026-08-15T19:21:35.855857Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T19:21:35.059834Z","title":"Deep unsupervised learning using nonequilibrium thermodynamics","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.059834Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:21a4c7b67df0df016ccf4c3cc5135fb9fa1e4b9ed46e284e71659e8abb4789c6","observation_id":"10e0ffc9-3391-41c9-b1a8-a69197dff213","resolution":{"observed_at":"2026-08-15T19:21:35.059834Z","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":"2026-08-15T19:21:35.835298Z","title":"Single image defocus deblurring using kernel-sharing parallel atrous convolutions","venue":null,"work_id":"aa7b9343-36ca-4cab-9557-35d79877f05c","year":2021},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.062893Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:674abf376e043cc05906614ea637465491f257db7a5effcf30ae1f3f49147f47","observation_id":"c939c5e4-809e-47d0-89fb-44f9c47672ff","resolution":{"observed_at":"2026-08-15T19:21:35.838611Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.13456","last_updated":"2021-02-10T18:17:04Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-11-26T19:39:10Z","title":"Score-Based Generative Modeling through Stochastic Differential Equations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.13456","snapshot_observed_at":"2026-08-15T19:21:35.065929Z","title":"Score- based generative modeling through stochastic differential equations.arXiv preprint arXiv:2011.13456, 2020","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.065929Z"},"links":{"cited_paper":"/paper/2011.13456","citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:12b9e9df398b020353fae82fccc500b4f91226766b6c8d1d20d861502d38b461","observation_id":"d1da3762-b8ef-49d0-b1aa-8c99952badbb","resolution":{"observed_at":"2026-08-15T19:21:35.065929Z","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":"2026-08-15T19:21:35.823838Z","title":"Transweather: Transformer-based restoration of im- ages degraded by adverse weather conditions","venue":null,"work_id":"abbe18ea-a8e5-4d10-9ecd-0c704fe72bfc","year":2022},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.069644Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:24dcb4bafaaa3b7c1ea7b099b3ed45c3f1856f6b6eeb8e9d38f8d191f81a219e","observation_id":"35296ca0-c6ac-4308-9333-7a400fbc1796","resolution":{"observed_at":"2026-08-15T19:21:35.827459Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T19:21:35.813423Z","title":"Spatial attentive single-image deraining with a high quality real rain dataset","venue":null,"work_id":"1ea7c8f7-9df5-4e81-a534-315ff3eb39d3","year":2019},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.073316Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:be1f159849f6cb52909ad6933482e6623942b86f5b351f0904587f33c54f7035","observation_id":"60603be5-fb58-4718-9c28-7568c6f2e98d","resolution":{"observed_at":"2026-08-15T19:21:35.817045Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T19:21:35.803235Z","title":"Esrgan: En- hanced super-resolution generative adversarial networks","venue":null,"work_id":"88100afa-ff7b-4ded-9fc3-213cd480e737","year":2018},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.076886Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:fb19874c4d923e71ca04763aab1440fe1cafb71d466d5bef985b7b4324309688","observation_id":"da943c52-6528-47f5-988d-fadfb976ad3b","resolution":{"observed_at":"2026-08-15T19:21:35.806917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T19:21:35.792649Z","title":"To- wards real-world blind face restoration with generative fa- cial prior","venue":null,"work_id":"28ae778a-0776-4f52-945d-2905d10e2192","year":2021},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.080632Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:d1753516b83967af192626997a98e05d215020184cc8969454b24fd8c45f708c","observation_id":"ba5fdde7-d643-4cfd-b099-11d7c981d1f8","resolution":{"observed_at":"2026-08-15T19:21:35.796139Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T19:21:35.782565Z","title":"Real-esrgan: Training real-world blind super-resolution with pure synthetic data","venue":null,"work_id":"abf168d0-df62-4e97-a5d5-8bc02ff545d6","year":1905},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.084084Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:2f38a38df791457ab59199ab53a1d20576888f8d7027613733b0691a7880ad0e","observation_id":"dee0b8ea-0bbc-4242-94db-79fb4205a11a","resolution":{"observed_at":"2026-08-15T19:21:35.785914Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-15T19:21:35.771899Z","title":"Low-light image enhancement with normalizing flow","venue":null,"work_id":"88fe9ec1-ceca-4f75-89eb-692d76705c89","year":2022},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.087930Z"},"links":{"citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:1b7dfcbf646d4fe05419aa05bd4dab33c7d179f85b5d62ca628797a6bce2ec96","observation_id":"5a7830de-49a1-473c-b4c8-2eab85edb164","resolution":{"observed_at":"2026-08-15T19:21:35.775804Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.00490","last_updated":"2022-12-07T13:29:20Z","snapshot_observed_at":"2026-08-19T15:28:44.366291Z","submitted_at":"2022-12-01T13:33:47Z","title":"Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.00490","snapshot_observed_at":"2026-08-15T19:21:35.091249Z","title":"Zero-shot im- age restoration using denoising diffusion null-space model","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-15T19:21:35.091249Z"},"links":{"cited_paper":"/paper/2212.00490","citing_paper":"/paper/2506.16961"},"observation_digest":"sha256:bce3cfb1b95c178b39ff72b858a3c4b11231f44c576a0614cb5384a34b379e8f","observation_id":"8517f544-1aae-4778-8d2f-32fa992da5f5","resolution":{"observed_at":"2026-08-15T19:21:35.091249Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.16961","last_updated":"2025-06-20T12:51:12Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T22:38:13.882942Z","submitted_at":"2025-06-20T12:51:12Z","title":"Reversing Flow for Image Restoration"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":74,"verified_exact":0,"verified_fuzzy":26},"total_outbound_references":135},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 100 of 135 outbound references and 0 inbound Pith citation observations for arXiv:2506.16961."}