{"as_of":"2026-08-10T20:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8a554f82818baa254df4afd3e7900e9491fa7adfe5182db2a157df91f662f3a2","coverage":[{"denominator":34,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":34,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-26T10:36:34.245210Z","state":"measured"},{"denominator":34,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":34,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2606.22696/citation-record","integrity":"/paper/2606.22696/integrity","json":"/paper/2606.22696/citation-record.json","paper":"/paper/2606.22696"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-26T10:36:34.245210Z","title":"Image super-resolution using deep convolutional networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:fa1d95537d84a2c4ec7bdfa9c4203ac8d1ef4dbd6b02fae6f4d4c7dffabd95f3","observation_id":"f150c82f-cc59-439f-aeec-2e1e1226dceb","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:a1f7a7f9dfdf47668774485afb3e28d7603beb9170ecf767a8343da9a00ff895","observation_id":"8e517ec0-ef91-4a62-826f-1a73c996d3b7","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Deep convolutional neural network for inverse problems in imaging,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:6c42984298474df8b1a029755d05455e43d4f9ef4f4d9203e7f1051996af3428","observation_id":"153dbc95-45e0-42c9-9adf-9e8b01106a62","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Deep null space learning for inverse problems: convergence analysis and rates,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:1eb0c8a0eed012af7572435deba1c62b4d4d5e7e876a1ee2b1cb8341c1fe0332","observation_id":"9a167962-c079-4e57-bb51-754c781bd97d","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Deep decomposition learning for inverse imaging problems,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:7200bf7dda6882e39ab83ea454274e2b8ba246ba2c0a04ba28777c50730d1a70","observation_id":"8bacbc8f-d778-4329-b7b5-56613c8065ba","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Provable convergence of plug-and-play priors with MMSE denoisers,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:f222061cc9a7955803d11048db59fc6001a23713ff821c5f0e59276df91c63fa","observation_id":"102416fc-0c6e-4224-8bae-cf38a9271fc6","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Plug-and-play image restoration with deep denoiser prior,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:34740cc2cd45b7704667ca30e7993737dabee23b15042abc28ad2bfcbb2f6278","observation_id":"cb1078e6-7ba6-4fba-99fc-95f5ea43e038","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Plug-and-play image restoration with stochastic denoising regularization,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:dd5505d6dd7b6b45f149315646529dac790ab5830bc6a81abaadeeeb277ad42a","observation_id":"26240283-454e-4b13-8efc-8cfd3fc9e866","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Denoising diffusion probabilistic models,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:94cfa14bbca6642190b630764e128f787c021daece07824ed5a531ef8801dbff","observation_id":"0a810a14-acfa-4663-b683-8421596c8218","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"High- resolution image synthesis with latent diffusion models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:89675288a5847549b5388d3aa136798fd05acc74552f630b05343e35776299a8","observation_id":"175c28da-bc8d-490d-86f0-5f8f34fece79","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Flow matching for generative modeling,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:9c998998e2bc92af76e091259f7136258d51fd7112159529885999fac21464d6","observation_id":"9dd5e3b1-b07a-4099-83a7-f7c7697c41ea","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Flow straight and fast: Learning to generate and transfer data with rectified flow,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:436ed6c7fe6a6ab411cff6cd760bba80ad5aea0470655fb131c6105a7fe2ab32","observation_id":"5f5ed4c4-a2f4-4952-8e0b-722c2308b4b5","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Building Normalizing Flows with Stochastic Interpolants,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:e34714ee610c6614fa2392f3970af499ecb0cf9888d4c60b628179398743d8c3","observation_id":"a99f8406-0ced-4f7d-87df-b4f3f187a415","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:aa8ac9371758a4deb08eca75716e7f67a5a9547f515f8690a4e9dd62e87d9d7d","observation_id":"32c48373-ac5c-467a-8dea-d668e85e5312","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Denoising diffusion restoration mod- els,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:cf6e4cf388009344b9b228cbab15dd075127163d945acdb17765917712c1e106","observation_id":"5a2c190a-b80f-495e-b27e-179b5acfedd4","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Diffusion posterior sampling for general noisy inverse problems,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:af280a757101ee135216886118af805a7fb82e5023f331452581ecc99cc077da","observation_id":"d99a9846-9572-4eaf-8f4e-f3558db7ec6d","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"DOLCE: A model-based probabilistic diffusion framework for limited-angle CT reconstruction,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:3953d8870b94736fb4960be87ba5728af48d924778b11185c0c23fee2d171fcf","observation_id":"b6ca6075-5050-497a-b7dd-59fead393134","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Stochastic Interpolants with Data-Dependent Couplings,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:6ad070772b48630011a18cef031de0d145a01bfa9030230cb05e5ea727a6fb7f","observation_id":"8db09eca-e86c-414b-a1fd-1cdc70cde1cc","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Plug-and-play methods for integrating physical and learned models in computational imaging,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:c6c184f8f44c20dda57d6245084284e5393d4ee3f1fe9f4949379a0a04b6e0ea","observation_id":"470ebbf5-a5a2-40db-beaf-ecc53fb63486","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.00083","last_updated":"2024-09-30T17:34:01Z","snapshot_observed_at":"2026-07-06T19:24:48.032228Z","submitted_at":"2024-09-30T17:34:01Z","title":"A Survey on Diffusion Models for Inverse Problems","version":1},"cited_work":{"arxiv_id":"2410.00083","doi":"10.48550/arxiv.2410.00083","metadata_source":"pith","pith_arxiv_id":"2410.00083","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"A Survey on Diffusion Models for Inverse Problems","venue":"cs.LG","work_id":"f2cbc6cc-8d87-4b5d-9751-74f49d4e3b63","year":2024},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"cited_paper":"/paper/2410.00083","citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:8d63df4bd1d99a56192c222d86bf8a9df0c6ab402571bb6533c3132f9fbfa73c","observation_id":"54512a3d-22f4-4ee9-b1e4-7c770a5e7c99","resolution":{"observed_at":"2026-07-04T08:59:43.387922Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-06-26T10:36:34.245210Z","title":"Zero-shot image restoration using denoising diffusion null- space model,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:6743ae53b6daf5e43ef36b67858caf0190709cfe1496f29fc2b5747ed95a1298","observation_id":"13805e17-460e-47e0-b9d5-97cac9b8bdd6","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Flowdps : Flow-driven posterior sampling for inverse problems,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:398a3c2a76dc5a688e12280207cfa7fdde9c9f5bc3ebf10d5bf2e78b8391f43b","observation_id":"c5ff0956-a7c4-4c05-9901-1c3277157aa3","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Flower: A Flow-Matching Solver for Inverse Problems,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:3ad818dcf41b21d489a7cca7592d5d7b33b71714fd55d605e4316bc1ca331baf","observation_id":"aeb995ea-de6b-4a1d-a49c-976663be8fa3","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Pnp-flow: Plug-and-play image restoration with flow matching,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:a91cc469372e72c8b0bf56f264f29d7495a3d393185a5b7b10d225f044a8ad3e","observation_id":"6682a013-9bb0-44d7-b6ed-834ec230a9f5","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Flow matching on general geometries,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:48664fafb7474d9debcedb0c7bc0290b3770855abe036618fcb67750c46bf3a5","observation_id":"7bcf63ca-66dc-4559-9294-0c45d233b3de","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"D-flow: Differen- tiating through flows for controlled generation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:431e560e1332c1cb610388f43c6236f540375850d7de4b397d8024b1e670a4f2","observation_id":"0c184bd9-04fe-4fec-b4be-96a50f0a3bac","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Flow priors for linear inverse problems via iterative corrupted trajectory matching,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:e1c43bb606c0761ff3d0feedcdffeb12cb2aad5874725d5056322fa16d8e1523","observation_id":"78bb1334-1034-4b4d-a3ae-2b36a6e34824","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Training-free linear image inverses via flows,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:4aac25ec2812958ec3085e80119babf3c86c1c55ff6c87e6f50c14183526d692","observation_id":"dafc4a8d-d250-4bef-a401-13985ce80965","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Mean flows for one- step generative modeling,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:14521dc9763f4b13d23b5d030542b46f051e8213f3cc754e1c06b83c86d2a9c8","observation_id":"6f9955cb-1963-4f84-99b3-51d59ff1df4a","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2512.02012","last_updated":"2026-05-09T17:02:52Z","snapshot_observed_at":"2026-08-06T20:59:53.475356Z","submitted_at":"2025-12-01T18:59:49Z","title":"Improved Mean Flows: On the Challenges of Fastforward Generative Models","version":2},"cited_work":{"arxiv_id":"2512.02012","doi":"10.48550/arxiv.2512.02012","metadata_source":"pith","pith_arxiv_id":"2512.02012","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Improved Mean Flows: On the Challenges of Fastforward Generative Models","venue":"cs.CV","work_id":"7cd9824a-ab63-446f-8fe9-99b288e3182d","year":2025},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"cited_paper":"/paper/2512.02012","citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:2af152afdb064d93c50428c3cc2cf6134148a78e011f210a864a8a31bf43f86b","observation_id":"e8090a98-43fe-4918-be47-2180fe79e23f","resolution":{"observed_at":"2026-07-04T08:59:43.385398Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2601.22158","last_updated":"2026-05-09T16:47:56Z","snapshot_observed_at":"2026-07-06T22:43:35.226546Z","submitted_at":"2026-01-29T18:59:56Z","title":"One-step Latent-free Image Generation with Pixel Mean Flows","version":3},"cited_work":{"arxiv_id":"2601.22158","doi":null,"metadata_source":"pith","pith_arxiv_id":"2601.22158","snapshot_observed_at":"2026-07-11T02:27:49.448130Z","title":"One-step Latent-free Image Generation with Pixel Mean Flows","venue":"cs.CV","work_id":"1f1b0766-5d88-4a61-ad93-652ceba56552","year":2026},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"cited_paper":"/paper/2601.22158","citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:4d734766430c770e02765da16d804cfd386ed3118c96f6dee85c46fbdd160885","observation_id":"87cefacb-5944-4eef-b1d8-13deb6eef9af","resolution":{"observed_at":"2026-07-04T08:59:43.390632Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-06-26T10:36:34.245210Z","title":"The unreasonable effectiveness of deep features as a perceptual metric,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:a937855f53f783198bc50eca091ea56de4d609eae4ccbb51446b787edb5ef7f4","observation_id":"721df1d3-f395-41ab-9bb5-4243e1c43ecb","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Convnext v2: Co-designing and scaling convnets with masked autoencoders,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:6586bb6c98bad53e1fbd2a5898b634193c2e52fe436d1e7f0d84fffe1ce1509b","observation_id":"40690d33-f69a-4f97-b3b1-978b1950db5a","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","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":"2026-06-26T10:36:34.245210Z","title":"Mean flows for one-step generative modeling,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-06-26T10:36:34.245210Z"},"links":{"citing_paper":"/paper/2606.22696"},"observation_digest":"sha256:be5706fc23d880abb2a1442a0e832d970a856b891faf03c796db2ccffc66717e","observation_id":"61ea3e84-0bde-4d77-a409-70d6deb8a8a9","resolution":{"observed_at":"2026-06-26T10:36:34.245210Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.22696","last_updated":"2026-06-21T22:21:43Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T06:34:40.607080Z","submitted_at":"2026-06-21T22:21:43Z","title":"NullFlow: One-Step Generative Reconstruction"},"reference_resolution":{"displayed":34,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":31,"verified_exact":3,"verified_fuzzy":0},"total_outbound_references":34},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 0 inbound Pith citation observations for arXiv:2606.22696."}