{"as_of":"2026-08-18T15:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3402da4305e69ea7ee74ba562fe44189e7ba85db46a3f30edc2d8dc2993dbd97","coverage":[{"denominator":54,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":54,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T22:03:03.675377Z","state":"measured"},{"denominator":58,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":58,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:36:26.525335Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-14T17:57:33.501777Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.18913","snapshot_observed_at":"2026-08-15T20:36:26.525335Z","title":"Rethinking diffusion posterior sampling: From conditional score estimator to maximizing a posterior","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.12486","last_updated":"2025-05-18T16:19:27Z","snapshot_observed_at":"2026-08-16T01:44:43.040648Z","submitted_at":"2025-05-18T16:19:27Z","title":"Guiding Diffusion with Deep Geometric Moments: Balancing Fidelity and Variation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:26.525335Z"},"links":{"cited_paper":"/paper/2501.18913","citing_paper":"/paper/2505.12486"},"observation_digest":"sha256:ad88cffcae88f55bdfcac2f06bf675d339cd21633c1e97176a2ed3a52b7977f8","observation_id":"9efd2332-8905-42f6-9efd-1fb45e0b3427","resolution":{"observed_at":"2026-08-15T20:36:26.525335Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.18913","snapshot_observed_at":"2026-08-04T11:15:57.735698Z","title":"Rethinking diffusion posterior sampling: From conditional score estimator to maximizing a posterior","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.07343","last_updated":"2026-05-24T18:40:06Z","snapshot_observed_at":"2026-08-17T23:11:14.438464Z","submitted_at":"2025-10-07T19:02:32Z","title":"Local MAP Sampling for Diffusion Models","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T11:15:57.735698Z"},"links":{"cited_paper":"/paper/2501.18913","citing_paper":"/paper/2510.07343"},"observation_digest":"sha256:de332194794a000045c0db17686b06d6c5bc8cd3a058bc2d40fc60ff65ca012a","observation_id":"4b3e1b9b-3c07-496b-ab4d-9ce83ba59677","resolution":{"observed_at":"2026-08-04T11:15:57.735698Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"cited_work":{"arxiv_id":"2501.18913","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.18913","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2501.18913 , year=","venue":null,"work_id":"3f8a9aad-c835-40b0-8e51-3d54d17c0b96","year":null},"citing_paper":{"arxiv_id":"2605.13278","last_updated":"2026-05-27T13:51:45Z","snapshot_observed_at":"2026-08-15T23:59:39.459943Z","submitted_at":"2026-05-13T09:55:51Z","title":"Proximal-Based Generative Modeling for Bayesian Inverse Problems","version":1},"reference_index":116,"source":"arxiv_source","source_observed_at":"2026-05-14T17:53:42.816596Z"},"links":{"cited_paper":"/paper/2501.18913","citing_paper":"/paper/2605.13278"},"observation_digest":"sha256:a0d8861663112f5052fcd915cc9254c36f9cfc8cc462584525269dae34532a89","observation_id":"0f9478e9-a6e2-4c52-a8c7-34142b1b8757","resolution":{"observed_at":"2026-05-14T17:57:33.504769Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.18913","snapshot_observed_at":"2026-07-11T23:10:33.541046Z","title":"arXiv preprint arXiv:2501.18913 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.03899","last_updated":"2026-07-04T14:44:06Z","snapshot_observed_at":"2026-08-08T19:28:26.365016Z","submitted_at":"2026-07-04T14:44:06Z","title":"DICT: Data Injection and Contrastive Trajectory Refinement for Conditional Image Generation with Diffusion Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-11T23:10:33.541046Z"},"links":{"cited_paper":"/paper/2501.18913","citing_paper":"/paper/2607.03899"},"observation_digest":"sha256:00ea46c6a47f3f106c8b0026a19e2dee0ffe3fcf83c0374a1532ab7346079dfb","observation_id":"da824421-b484-4eb6-a092-cc6962810c49","resolution":{"observed_at":"2026-07-11T23:10:33.541046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2501.18913/citation-record","integrity":"/paper/2501.18913/integrity","json":"/paper/2501.18913/citation-record.json","paper":"/paper/2501.18913"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T22:03:04.444556Z","title":"Universal guidance for diffusion models","venue":null,"work_id":"609cb095-d361-4e7e-b5a1-9796ed20df45","year":2023},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.439137Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:386042d3aaeefe6c3a18397f1b270794702377c1ed8d1f8cf17180345dd7311d","observation_id":"7374ec49-89bd-4889-b7c1-ed755df1cdf3","resolution":{"observed_at":"2026-08-09T22:03:04.448982Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1801.01401","last_updated":"2021-01-14T05:36:59Z","snapshot_observed_at":"2026-08-13T06:40:48.610500Z","submitted_at":"2018-01-04T15:25:26Z","title":"Demystifying MMD GANs","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.01401","snapshot_observed_at":"2026-08-09T22:03:03.443926Z","title":"Sutherland, Michal Arbel, and Arthur Gretton","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.443926Z"},"links":{"cited_paper":"/paper/1801.01401","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:11187ba2bdd19f9b132156f6ad6594317d9151a89bf78821e31be37cf2633a0b","observation_id":"5c3980fd-6787-40b1-b5ae-3fb6b25f1553","resolution":{"observed_at":"2026-08-09T22:03:03.443926Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06721","last_updated":"2024-09-25T13:27:22Z","snapshot_observed_at":"2026-08-17T21:57:03.905714Z","submitted_at":"2023-10-10T15:48:55Z","title":"Tweedie Moment Projected Diffusions For Inverse Problems","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06721","snapshot_observed_at":"2026-08-09T22:03:03.448848Z","title":"Tweedie moment projected diffusions for inverse problems","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.448848Z"},"links":{"cited_paper":"/paper/2310.06721","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:a19c84ad1b1f83baf40e0aa733429bfc1ab4f5c61e52621fb660baec26fafe15","observation_id":"3ef8b8de-7c07-4520-8ab2-5f0853a0d537","resolution":{"observed_at":"2026-08-09T22:03:03.448848Z","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":"2026-08-09T22:03:03.453342Z","title":"Monte carlo guided denoising diffusion models for bayesian linear inverse problems","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.453342Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:0f6a734260e3682ae7979de3ad4027da02165ad8d025997dd55b97c9ee94ce03","observation_id":"8a4a3e95-e96d-49d4-8143-f5857bc0be78","resolution":{"observed_at":"2026-08-09T22:03:03.453342Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.14687","last_updated":"2024-05-20T04:23:45Z","snapshot_observed_at":"2026-08-14T03:13:28.801183Z","submitted_at":"2022-09-29T11:12:27Z","title":"Diffusion Posterior Sampling for General Noisy Inverse Problems","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.14687","snapshot_observed_at":"2026-08-09T22:03:03.457774Z","title":"McCann, Marc Louis Klasky, and J","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.457774Z"},"links":{"cited_paper":"/paper/2209.14687","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:292f48dcb563a63fceab303750491323036e54a4eaf41cd2ea77f6f824352f86","observation_id":"e7e9d2b7-967f-4d34-ae6c-16bf4cc44cb3","resolution":{"observed_at":"2026-08-09T22:03:03.457774Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.00941","last_updated":"2024-05-20T04:05:20Z","snapshot_observed_at":"2026-08-16T16:55:48.344890Z","submitted_at":"2022-06-02T09:06:10Z","title":"Improving Diffusion Models for Inverse Problems using Manifold Constraints","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.00941","snapshot_observed_at":"2026-08-09T22:03:03.462293Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.462293Z"},"links":{"cited_paper":"/paper/2206.00941","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:4f94e74f53a3a5bc21c33f4b31b3bd31df7f1570f9c061c37c829779f041509f","observation_id":"fc9fc221-5b8d-42aa-8915-bf9083550b98","resolution":{"observed_at":"2026-08-09T22:03:03.462293Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.01110","last_updated":"2023-10-02T11:31:48Z","snapshot_observed_at":"2026-08-16T14:55:54.568010Z","submitted_at":"2023-10-02T11:31:48Z","title":"Prompt-tuning latent diffusion models for inverse problems","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.01110","snapshot_observed_at":"2026-08-09T22:03:03.467364Z","title":"Prompt-tuning latent diffusion models for inverse problems","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.467364Z"},"links":{"cited_paper":"/paper/2310.01110","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:faf4e84f5311782ed0e07dedfb280d284afb187e6da7005019fdb32c7ca49689","observation_id":"81b28e05-ddcb-446b-968b-9aca3fc77d30","resolution":{"observed_at":"2026-08-09T22:03:03.467364Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.16047","last_updated":"2024-03-11T15:14:51Z","snapshot_observed_at":"2026-08-16T14:49:14.721910Z","submitted_at":"2023-10-24T17:58:54Z","title":"From Posterior Sampling to Meaningful Diversity in Image Restoration","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.16047","snapshot_observed_at":"2026-08-09T22:03:03.471760Z","title":"From posterior sampling to meaningful diversity in image restoration","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.471760Z"},"links":{"cited_paper":"/paper/2310.16047","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:9dfa16b714c970d7c8b3341f877cdb52e78ee719ed2ae0210c3a9bf6edd07357","observation_id":"6bad0aba-94a0-47fd-838a-9bc0119cd55f","resolution":{"observed_at":"2026-08-09T22:03:03.471760Z","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":"2026-08-09T22:03:03.476240Z","title":"Elements of information theory","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.476240Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:8eac32a3489e89c4d2e0eaab4ab70da2824d67e00c2c92cf3320a46b7ac119d1","observation_id":"f0095b0b-5d52-402e-9ca7-9d58efa1ac65","resolution":{"observed_at":"2026-08-09T22:03:03.476240Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.15996","last_updated":"2023-11-27T16:44:50Z","snapshot_observed_at":"2026-08-16T14:39:58.359660Z","submitted_at":"2023-11-27T16:44:50Z","title":"Closing the ODE-SDE gap in score-based diffusion models through the Fokker-Planck equation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.15996","snapshot_observed_at":"2026-08-09T22:03:03.480220Z","title":"Closing the ode-sde gap in score-based diffusion models through the fokker-planck equation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.480220Z"},"links":{"cited_paper":"/paper/2311.15996","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:fea345df0002656b72488f3ce78b974caa881bae79e65a4a15fb140d50084c72","observation_id":"c5b6a65b-1432-4746-a53f-727141de461c","resolution":{"observed_at":"2026-08-09T22:03:03.480220Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.05233","last_updated":"2021-06-01T17:49:49Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2021-05-11T17:50:24Z","title":"Diffusion Models Beat GANs on Image Synthesis","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.05233","snapshot_observed_at":"2026-08-09T22:03:03.484693Z","title":"Diffusion models beat gans on image synthesis","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.484693Z"},"links":{"cited_paper":"/paper/2105.05233","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:55e069a2009fe77a7e0c84a1ea35dada3ea035274486c0611d72f6de7a5ce406","observation_id":"3f5450df-dc39-4fb6-abbd-d63bda45aaf3","resolution":{"observed_at":"2026-08-09T22:03:03.484693Z","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":"2026-08-09T22:03:04.409226Z","title":"Diffusion posterior sampling for linear inverse problem solving: A filtering perspective","venue":null,"work_id":"fa9d4ce8-4992-44d6-bd93-dc4d4e668b31","year":2023},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.488952Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:c263120093b6fccdd6633231ce7647b118122eba3b56b1747d08a96bf48d3141","observation_id":"83f673df-20a5-4588-b241-1935f13fce7d","resolution":{"observed_at":"2026-08-09T22:03:04.414504Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T22:03:03.492952Z","title":"Diffusion posterior sampling for linear inverse problem solving: A filtering perspective","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.492952Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:473aad6f9c2fcaf87580d674ada3cca02aad5df827ebac98bf88802e2553cb85","observation_id":"e677aac5-1b84-40ce-83bf-c359ec1b0b36","resolution":{"observed_at":"2026-08-09T22:03:03.492952Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.11751","last_updated":"2023-08-28T22:38:31Z","snapshot_observed_at":"2026-08-16T16:46:06.591550Z","submitted_at":"2023-04-23T21:05:59Z","title":"Score-Based Diffusion Models as Principled Priors for Inverse Imaging","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.11751","snapshot_observed_at":"2026-08-09T22:03:03.496861Z","title":"Score-based diffusion models as principled priors for inverse imaging","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.496861Z"},"links":{"cited_paper":"/paper/2304.11751","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:c45d5cb6a900498056c37ae4609dbf470cacd5e4aa2b85efd51aee317f3fd7d8","observation_id":"7c84933c-99b6-4fb8-84e5-085b3bca2ad9","resolution":{"observed_at":"2026-08-09T22:03:03.496861Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.20784","last_updated":"2024-09-18T14:01:47Z","snapshot_observed_at":"2026-08-18T11:37:47.646213Z","submitted_at":"2024-07-27T15:41:13Z","title":"Inverse Problems with Diffusion Models: A MAP Estimation Perspective","version":2},"cited_work":{"arxiv_id":"2407.20784","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.20784","snapshot_observed_at":"2026-08-09T22:03:03.968945Z","title":"Inverse Problems with Diffusion Models: A MAP Estimation Perspective","venue":"cs.CV","work_id":"666d91be-3d4d-418a-acf7-51505fed17bc","year":2024},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.500994Z"},"links":{"cited_paper":"/paper/2407.20784","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:59d37bb9dfbbf4372ef091278db00847dd3e27baa7bdf08fa2e85ce0ba34ad3a","observation_id":"e1745474-ba14-45b9-b783-e67705b01f12","resolution":{"observed_at":"2026-08-09T22:03:03.973834Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T22:03:04.384596Z","title":"Fast and stable diffusion inverse solver with history gradient update","venue":null,"work_id":"3db94588-dc09-4fdf-9d55-d8577aeb81f8","year":2023},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.504949Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:ca66342704f22ebfe632ca4d11b624ffdc8ff951ba99b99475d5d359eeb2dc21","observation_id":"1be50626-7b12-46ab-8801-2403585fa6d8","resolution":{"observed_at":"2026-08-09T22:03:04.389394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T22:03:04.371182Z","title":"Manifold preserving guided diffusion","venue":null,"work_id":"a7a75c6e-4bcd-49f4-ae6a-db780b674b1f","year":2024},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.508798Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:bd15458baf360236db9d6123e4663a021f1d666eb65758c3b9e54a061d2438a0","observation_id":"61e88fef-ae40-483c-9f76-a1d749b31725","resolution":{"observed_at":"2026-08-09T22:03:04.375428Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T22:03:04.357123Z","title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","venue":null,"work_id":"3798f1c2-21b4-4751-92c1-d7aee5446958","year":2017},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.512633Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:04f10aad36d755b6ff490678a7e4ccccae71576914a6e03beb909171dc4462e8","observation_id":"3d604d60-afc7-4130-9319-776a50f672eb","resolution":{"observed_at":"2026-08-09T22:03:04.361553Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T22:03:03.516680Z","title":"Denoising diffusion probabilistic models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.516680Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:6fc4e7ecca5d5c3b9abfb5dcd4b4432fed14d92de83f6479ea95b19409676303","observation_id":"d137bd01-df16-4dc6-baba-3bcd4a729cd1","resolution":{"observed_at":"2026-08-09T22:03:03.516680Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.11407","last_updated":"2024-11-11T15:31:42Z","snapshot_observed_at":"2026-08-16T14:08:58.983503Z","submitted_at":"2024-03-18T01:47:24Z","title":"Divide-and-Conquer Posterior Sampling for Denoising Diffusion Priors","version":2},"cited_work":{"arxiv_id":"2403.11407","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.11407","snapshot_observed_at":"2026-08-09T22:03:03.948418Z","title":"Divide-and-Conquer Posterior Sampling for Denoising Diffusion Priors","venue":"stat.ML","work_id":"fd2a94a6-a6a1-4682-a562-b3312814e542","year":2024},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.520302Z"},"links":{"cited_paper":"/paper/2403.11407","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:20bb80b0e48dc951b551c669d2a35967f62e19d2f7370682ac833a4835d7e821","observation_id":"bed286e8-6d8c-4cda-aa32-22be3d542a7d","resolution":{"observed_at":"2026-08-09T22:03:03.953232Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.00364","last_updated":"2022-10-11T13:20:30Z","snapshot_observed_at":"2026-07-06T13:16:16.926712Z","submitted_at":"2022-06-01T10:03:24Z","title":"Elucidating the Design Space of Diffusion-Based Generative Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.00364","snapshot_observed_at":"2026-08-09T22:03:03.524273Z","title":"Elucidating the design space of diffusion-based generative models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.524273Z"},"links":{"cited_paper":"/paper/2206.00364","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:c5c5b1cb3a597005235bfcdb952626f6b0673097a8353b2a01738c55f1476f9c","observation_id":"f8b89cc1-8fd3-458e-9fa9-a1edde8f276e","resolution":{"observed_at":"2026-08-09T22:03:03.524273Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.11793","last_updated":"2022-10-12T18:56:53Z","snapshot_observed_at":"2026-08-16T17:25:25.172204Z","submitted_at":"2022-01-27T20:19:07Z","title":"Denoising Diffusion Restoration Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.11793","snapshot_observed_at":"2026-08-09T22:03:03.528073Z","title":"Denoising diffusion restoration models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.528073Z"},"links":{"cited_paper":"/paper/2201.11793","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:de6a41174f891db025c0289d20fd431314963454ef2a4ac418907876dabf60f5","observation_id":"7a44025a-19ed-46f2-b277-f14179588813","resolution":{"observed_at":"2026-08-09T22:03:03.528073Z","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":"2026-08-09T22:03:03.532088Z","title":"Kingma and Jimmy Ba","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.532088Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:513e2201a187e04770456d1f49ec71d013c49180ac75646afc3d9fd8e811d05b","observation_id":"69be5633-3982-4f7f-a2aa-c2ab0837521f","resolution":{"observed_at":"2026-08-09T22:03:03.532088Z","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":"2026-08-09T22:03:04.333082Z","title":"Indoor scene layout estimation from a single image","venue":null,"work_id":"03869858-5525-40f9-ae2e-4e8f9bc7bfb0","year":2018},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.536704Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:4a46ebc1f221dd011ab453561f7dc102bdb41a5efc2eae6520c746aa85dde37b","observation_id":"cecc490f-8b54-424b-9d81-e3e76d682ce1","resolution":{"observed_at":"2026-08-09T22:03:04.337467Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2026-08-09T22:03:03.540883Z","title":"Flow matching for generative modeling","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.540883Z"},"links":{"cited_paper":"/paper/2210.02747","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:dfb261a89929e9ce5207a555f0fe2890ba153e9b3488176501a66815b206e9f3","observation_id":"f358045b-93e3-4eeb-a12e-96cf1b46f716","resolution":{"observed_at":"2026-08-09T22:03:03.540883Z","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":"2026-08-09T22:03:04.319249Z","title":"Repaint: Inpainting using denoising diffusion probabilistic models","venue":null,"work_id":"37bb7b48-0317-4792-aa4c-1996df001481","year":2022},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.545158Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:1158aed1bbffd386053557014b1703b1404abe226faad082437dc7a953bf806a","observation_id":"56e74ee1-96f8-4f4a-8baf-e25191bacfb5","resolution":{"observed_at":"2026-08-09T22:03:04.323755Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.04391","last_updated":"2023-09-29T18:22:58Z","snapshot_observed_at":"2026-08-18T14:05:09.661338Z","submitted_at":"2023-05-07T23:00:47Z","title":"A Variational Perspective on Solving Inverse Problems with Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.04391","snapshot_observed_at":"2026-08-09T22:03:03.557319Z","title":"A variational perspective on solving inverse problems with diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.557319Z"},"links":{"cited_paper":"/paper/2305.04391","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:0ab47504bb8d2bed0e76db44c45c1fd010cbc26dd7b200de813abf5de011e98c","observation_id":"74a13cb2-7d78-45a8-a2f9-d63583e464dd","resolution":{"observed_at":"2026-08-09T22:03:03.557319Z","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":"2026-08-09T22:03:04.305416Z","title":"Pulse: Self-supervised photo upsampling via latent space exploration of generative models","venue":null,"work_id":"a526ad9b-3a1f-43c9-87f2-d13d17d25076","year":2020},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.561292Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:76475f68f3199617c973f96a8ca47d396ad90b031cca19918ac0a015e17bd85d","observation_id":"b57befb4-8a44-4b9e-9b9e-0fb5de6d2ec3","resolution":{"observed_at":"2026-08-09T22:03:04.309666Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T22:03:03.565313Z","title":"Variational inference for monte carlo objectives","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.565313Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:b62f79c6713099380cc07aa7d9a37ceda56e7c5a904b0e97495772f80e91d699","observation_id":"c2dc667e-104d-4260-a0e3-c7ed5fb51261","resolution":{"observed_at":"2026-08-09T22:03:03.565313Z","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":"2026-08-09T22:03:03.569391Z","title":"Monte carlo gradient estimation in machine learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.569391Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:e688e9f331e8cd2b771f2c829e2e4b59391328c02b41c00899dc0cbf4b1b026a","observation_id":"c1abb10c-364b-4df5-91ed-435f53e15275","resolution":{"observed_at":"2026-08-09T22:03:03.569391Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.06320","last_updated":"2024-06-15T11:28:05Z","snapshot_observed_at":"2026-08-16T14:19:56.163514Z","submitted_at":"2024-02-09T11:01:35Z","title":"Particle Denoising Diffusion Sampler","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.06320","snapshot_observed_at":"2026-08-09T22:03:03.573500Z","title":"Particle denoising diffusion sampler","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.573500Z"},"links":{"cited_paper":"/paper/2402.06320","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:c74cd36902400f832a3cc40dae72aae329f6699459805417f026e020f2c42adf","observation_id":"c0bae980-74aa-41e4-83ad-cc6f9c001f91","resolution":{"observed_at":"2026-08-09T22:03:03.573500Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04432","last_updated":"2024-03-10T22:01:18Z","snapshot_observed_at":"2026-08-16T14:57:41.845664Z","submitted_at":"2023-09-25T22:13:16Z","title":"Training-free Linear Image Inverses via Flows","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.04432","snapshot_observed_at":"2026-08-09T22:03:03.577862Z","title":"Training-free linear image inversion via flows","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.577862Z"},"links":{"cited_paper":"/paper/2310.04432","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:15c9ac223a924f3c77b9b866a3c473792769a5f1c2dab96e87adcf316a99d95d","observation_id":"2a49ab3b-d6e0-428f-9abc-55796ff64b9d","resolution":{"observed_at":"2026-08-09T22:03:03.577862Z","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":"2026-08-09T22:03:04.271388Z","title":"Muckley, Ricky T","venue":null,"work_id":"6101b70d-9f83-44fa-8709-8fb699b1a86b","year":2024},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.582037Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:7ef721cd0db818619c7185f090b41a8444c69de5af9b4cd9397930a01e0ba9df","observation_id":"b28e8408-1894-4b74-9946-d5a91d652ce9","resolution":{"observed_at":"2026-08-09T22:03:04.275749Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.00852","last_updated":"2023-12-01T14:36:24Z","snapshot_observed_at":"2026-08-17T03:32:59.821992Z","submitted_at":"2023-12-01T14:36:24Z","title":"Beyond First-Order Tweedie: Solving Inverse Problems using Latent Diffusion","version":1},"cited_work":{"arxiv_id":"2312.00852","doi":null,"metadata_source":"pith","pith_arxiv_id":"2312.00852","snapshot_observed_at":"2026-08-09T22:03:03.817483Z","title":"Beyond First-Order Tweedie: Solving Inverse Problems using Latent Diffusion","venue":"cs.LG","work_id":"ce268645-fc05-49f1-a22a-5e097b6f658c","year":2023},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.586224Z"},"links":{"cited_paper":"/paper/2312.00852","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:69509a67151673337da8706c5402fc4ec35ec73fd2fe6a65421cf920e311650d","observation_id":"a72e1a13-bba2-4adb-8a0e-2901d4708ec4","resolution":{"observed_at":"2026-08-09T22:03:03.824325Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T22:03:04.256999Z","title":"Solving linear inverse problems provably via posterior sampling with latent diffusion models","venue":null,"work_id":"cf220fb2-b5ba-43a5-a794-f1e5aa5caad2","year":2024},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.590358Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:7a794e7fe35e8da203364a9af9dffd11ec5e9b6f10442a56294b8f43f51edc4c","observation_id":"4ea16cb3-767f-4393-b6d6-eda40ff2e1cf","resolution":{"observed_at":"2026-08-09T22:03:04.261348Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T22:03:03.594207Z","title":"Deep unsupervised learning using nonequilibrium thermodynamics","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.594207Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:b8c47a1a0762fc3a1138020a8512ea2e321e043738dc0496b5020b5e37178481","observation_id":"a15c5f3c-566c-447e-895e-18b3002fbe7b","resolution":{"observed_at":"2026-08-09T22:03:03.594207Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.08123","last_updated":"2024-04-16T02:37:47Z","snapshot_observed_at":"2026-08-16T15:15:52.466628Z","submitted_at":"2023-07-16T18:42:01Z","title":"Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.08123","snapshot_observed_at":"2026-08-09T22:03:03.598333Z","title":"Solving inverse problems with latent diffusion models via hard data consistency","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.598333Z"},"links":{"cited_paper":"/paper/2307.08123","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:ebd37e6833ae3da9c1c4bb8dda77544cd13e5170e7eef9d5dff46cea517739de","observation_id":"6988c5a3-27d4-45c4-98d6-cade3367f98c","resolution":{"observed_at":"2026-08-09T22:03:03.598333Z","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":"2026-08-09T22:03:04.233000Z","title":"Pseudoinverse-guided diffusion models for inverse problems","venue":null,"work_id":"ea44e638-b9f4-4a7f-8833-bb56618ee287","year":2022},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.602423Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:3caee7b3392f0e555d88d43b8078fbac5409d5412d4cf1575373cf4450bbb32b","observation_id":"1b668e2e-3d33-4096-9d9f-baf854171f1d","resolution":{"observed_at":"2026-08-09T22:03:04.237202Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T22:03:04.219447Z","title":"Pseudoinverse-guided diffusion models for inverse problems","venue":null,"work_id":"02a2cc96-ef16-426c-9e67-1cd09651fb76","year":2023},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.606344Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:f452b5cab4cb05fda5e53d651f35e5949eb1d3f3d304047d20401f5ee646a015","observation_id":"86ad822d-82a6-4f40-abdd-423f7fb57475","resolution":{"observed_at":"2026-08-09T22:03:04.223751Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T22:03:04.206179Z","title":"Loss-guided diffusion models for plug-and-play controllable generation","venue":null,"work_id":"874c55a2-d62a-43da-9b09-99abb8829710","year":2023},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.610166Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:746af99831f4b4d9fa5382c912ce00d1224129eca5541e393d2f00d1562ec24c","observation_id":"c696d237-c751-476b-ad6f-f2b7beb1dce8","resolution":{"observed_at":"2026-08-09T22:03:04.210266Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T22:03:03.614028Z","title":"Score-based generative modeling through stochastic differential equations","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.614028Z"},"links":{"cited_paper":"/paper/2011.13456","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:79ad732ac28fb17508ce514aed4337d40cadfb723d291da969abdc6c50f857f4","observation_id":"2215dcf7-04fe-46fd-b20a-0395df677c43","resolution":{"observed_at":"2026-08-09T22:03:03.614028Z","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":"2026-08-09T22:03:04.192046Z","title":"Exploiting diffusion prior for real-world image super-resolution","venue":null,"work_id":"f88380b7-2411-459d-b1fc-1dcd5523d8f8","year":2024},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.618555Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:16b3edbc60aa0eb93b82b5b5d0c56c70536236a26631480ca49fd0e4e4253459","observation_id":"73dc23fc-633f-460d-ac9f-d9340e3ef080","resolution":{"observed_at":"2026-08-09T22:03:04.196336Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.00490","last_updated":"2022-12-07T13:29:20Z","snapshot_observed_at":"2026-08-16T16:11:46.075018Z","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":"2026-08-09T22:03:03.622532Z","title":"Zero-shot image restoration using denoising diffusion null-space model","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.622532Z"},"links":{"cited_paper":"/paper/2212.00490","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:5ca35abb5e3f87dcdb3cf10a071e1bff9b52e5bf240ebe728c0c6da3ee1f1bf4","observation_id":"6426d84b-606c-456d-8051-81d87db6dba4","resolution":{"observed_at":"2026-08-09T22:03:03.622532Z","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":"2026-08-09T22:03:03.626674Z","title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.626674Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:680748d3f003203ccc01058a0ee490b1ee5b4d204e4bd4ab2dc2074ce9e41e9e","observation_id":"49955ba3-431d-47b1-aa1b-3b9ffe345455","resolution":{"observed_at":"2026-08-09T22:03:03.626674Z","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":"2026-08-09T22:03:03.630513Z","title":"Practical and asymptotically exact conditional sampling in diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.630513Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:508d870af0b4745dcf0f0101eece7d4fb21725f5566f04dac317fdfedfea62e7","observation_id":"35e41287-91c3-420a-8fbc-0bbbfdc57233","resolution":{"observed_at":"2026-08-09T22:03:03.630513Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03201","last_updated":"2024-07-04T08:58:36Z","snapshot_observed_at":"2026-08-16T14:21:20.655612Z","submitted_at":"2024-02-05T17:12:21Z","title":"Guidance with Spherical Gaussian Constraint for Conditional Diffusion","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03201","snapshot_observed_at":"2026-08-09T22:03:03.634351Z","title":"Guidance with spherical gaussian constraint for conditional diffusion","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.634351Z"},"links":{"cited_paper":"/paper/2402.03201","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:03e777a206dd488e75a1e8175937267eca6ddcff9c62f4559fd621ec404b3cdb","observation_id":"90c7cb65-9bcc-45e1-b254-0d4a07d78c8d","resolution":{"observed_at":"2026-08-09T22:03:03.634351Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.09833","last_updated":"2023-03-17T08:38:33Z","snapshot_observed_at":"2026-08-16T15:47:28.892786Z","submitted_at":"2023-03-17T08:38:33Z","title":"FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.09833","snapshot_observed_at":"2026-08-09T22:03:03.638250Z","title":"Freedom: Training-free energy-guided conditional diffusion model","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.638250Z"},"links":{"cited_paper":"/paper/2303.09833","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:b07d544433a37f2fdd7c313e42e247aca1c33118f9b8ec3e07c379fe68a86636","observation_id":"4a574f21-ffa9-4889-875f-f6a7db0d606f","resolution":{"observed_at":"2026-08-09T22:03:03.638250Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.01521","last_updated":"2025-08-15T22:30:53Z","snapshot_observed_at":"2026-08-17T02:24:41.614830Z","submitted_at":"2024-07-01T17:59:23Z","title":"Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.01521","snapshot_observed_at":"2026-08-09T22:03:03.648803Z","title":"Improving diffusion inverse problem solving with decoupled noise annealing","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.648803Z"},"links":{"cited_paper":"/paper/2407.01521","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:4c094759b8a169e60ee2f4e8945ce5cb8ee44e7b5008b80d2350b7467d20d729","observation_id":"a5428278-d932-4857-a657-43115ba2a063","resolution":{"observed_at":"2026-08-09T22:03:03.648803Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.05543","last_updated":"2023-11-26T22:26:12Z","snapshot_observed_at":"2026-08-14T19:07:37.876970Z","submitted_at":"2023-02-10T23:12:37Z","title":"Adding Conditional Control to Text-to-Image Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.05543","snapshot_observed_at":"2026-08-09T22:03:03.653336Z","title":"Adding conditional control to text-to-image diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.653336Z"},"links":{"cited_paper":"/paper/2302.05543","citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:c35fbc70de163a1185901d5fadc06c26454e5382ad584ab3a0d1d1c05046e8e6","observation_id":"35b9bafd-5fae-4503-b7bc-ab4d5141d0da","resolution":{"observed_at":"2026-08-09T22:03:03.653336Z","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":"2026-08-09T22:03:04.159141Z","title":"Efros, Eli Shechtman, and Oliver Wang","venue":null,"work_id":"e5d8a0ab-1e9b-4302-a981-3bcaf5d27cb1","year":2018},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.657665Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:0c335029581ae700c2c63cb730734bacb5f156b31487ef21409f7749fd7bc4be","observation_id":"a0927452-b9a5-4bdc-a005-7b7bc2d4ccf6","resolution":{"observed_at":"2026-08-09T22:03:04.163404Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-09T22:03:03.661665Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.661665Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:c4a8cbee86df4f0e8fc4f79887864786ad191001bc632c9497c7cbab512cdfda","observation_id":"b0a0ddd2-aead-452f-ad25-0ca690591e34","resolution":{"observed_at":"2026-08-09T22:03:03.661665Z","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":"2026-08-09T22:03:03.666815Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.666815Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:3def948fcc2975f90bf15a7c4cfedbd31656958de36d9fb49a23be509989476c","observation_id":"82887540-f108-41c6-bf97-118b1779918b","resolution":{"observed_at":"2026-08-09T22:03:03.666815Z","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":"2026-08-09T22:03:03.671148Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.671148Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:f3b6beace8046fc7b6d9db2ccc94f42df10e8c9bfa041f50fd64e501c180b0b0","observation_id":"7fe8e2df-c950-4a0f-b690-9f8ee85999e7","resolution":{"observed_at":"2026-08-09T22:03:03.671148Z","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":"2026-08-09T22:03:03.675377Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior","version":2},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-09T22:03:03.675377Z"},"links":{"citing_paper":"/paper/2501.18913"},"observation_digest":"sha256:afaed914cdeac8ae1495f74d0c7a11e96774be3aa5a6b0d5607a1d1726a3087a","observation_id":"3966f370-979e-4762-9b80-eb40fa093411","resolution":{"observed_at":"2026-08-09T22:03:03.675377Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2501.18913","last_updated":"2025-06-03T02:58:07Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-17T20:52:53.742647Z","submitted_at":"2025-01-31T06:26:19Z","title":"Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior"},"reference_resolution":{"displayed":54,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":36,"verified_exact":3,"verified_fuzzy":15},"total_outbound_references":54},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 4 inbound Pith citation observations for arXiv:2501.18913."}