{"as_of":"2026-08-14T17:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:732cb6dae0c329d9159b911caca4cf552ae40ef42fff331d87579ee5e08bb063","coverage":[{"denominator":45,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":45,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:05:46.193531Z","state":"measured"},{"denominator":47,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":47,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-27T05:54:23.709309Z","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":"2026-07-03T16:18:37.950110Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"cited_work":{"arxiv_id":"2505.22841","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.22841","snapshot_observed_at":"2026-07-03T16:18:37.950110Z","title":"Kernel-smoothed scores for denoising diffusion: A bias-variance study","venue":null,"work_id":"d35c1389-5f89-4af4-a7e2-0fcbc754a43c","year":2025},"citing_paper":{"arxiv_id":"2605.14276","last_updated":"2026-05-14T02:20:36Z","snapshot_observed_at":"2026-08-11T17:33:15.788769Z","submitted_at":"2026-05-14T02:20:36Z","title":"Training-Free Generative Sampling via Moment-Matched Score Smoothing","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-15T02:31:15.134624Z"},"links":{"cited_paper":"/paper/2505.22841","citing_paper":"/paper/2605.14276"},"observation_digest":"sha256:b360d56e5933379f97dde10e154f4c8e27e5fdcd042646c4d8fd2a406df3aece","observation_id":"55702467-afd3-4775-96d8-f5df94dca12a","resolution":{"observed_at":"2026-05-15T02:33:32.412238Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"cited_work":{"arxiv_id":"2505.22841","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.22841","snapshot_observed_at":"2026-07-03T16:18:37.950110Z","title":"Kernel-smoothed scores for denoising diffusion: A bias-variance study","venue":null,"work_id":"d35c1389-5f89-4af4-a7e2-0fcbc754a43c","year":2025},"citing_paper":{"arxiv_id":"2606.13433","last_updated":"2026-06-11T14:58:30Z","snapshot_observed_at":"2026-08-06T09:23:10.403105Z","submitted_at":"2026-06-11T14:58:30Z","title":"Smoothed-KL Reweighting: A Principled Account and Matching Rule for SNR-Based Diffusion Training","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-27T05:54:23.709309Z"},"links":{"cited_paper":"/paper/2505.22841","citing_paper":"/paper/2606.13433"},"observation_digest":"sha256:a777a3c14f21bbe60e3ebae9fb820ea769c12c08f078cc13dd3eabbb7fb44e89","observation_id":"fcf745ff-75e8-4b96-9767-cdc36a03812d","resolution":{"observed_at":"2026-07-03T16:18:37.951603Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.22841/citation-record","integrity":"/paper/2505.22841/integrity","json":"/paper/2505.22841/citation-record.json","paper":"/paper/2505.22841"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:52.227728Z","title":"Matrix algebra, volume 1","venue":null,"work_id":"e6b2b1db-94ef-4181-bd0e-5776ecf6eeb4","year":2005},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:42.861170Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:38ef9bff5476501fc7b1b5ccac55bbc6b22cc602fe3eabce6dcf059679664cd8","observation_id":"f1c8fc52-df36-4a53-bfad-29a97f7547bf","resolution":{"observed_at":"2026-08-07T13:05:52.280400Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:52.094396Z","title":"Losing dimensions: Geometric memorization in generative diffusion, 2024","venue":null,"work_id":"d8cde76a-5a4a-47c3-8b76-4da241e82245","year":2024},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:42.892664Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:d16254f79e8366e3abc39cac2f98f03ad6f38922a5bdb33c8bf8f15382c0ca1f","observation_id":"3d741a22-3574-41b6-9d57-6d74fa131959","resolution":{"observed_at":"2026-08-07T13:05:52.152184Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:51.948941Z","title":"Anderson","venue":null,"work_id":"de5777d3-fe91-4862-98de-8888cca7e41c","year":1982},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:42.974940Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:2f47a23a25e3d36ba5f8ff279dc4eddba33b4a797a79b595fcc9296abc01aba9","observation_id":"1dc0e694-ff99-4b68-8b77-1967eb1f590a","resolution":{"observed_at":"2026-08-07T13:05:51.997986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:51.810905Z","title":"Kovachki, Assad Oberai, and Andrew M","venue":null,"work_id":"9c00cd57-9856-4280-9623-3689bbc6d550","year":2025},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:43.040536Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:ac34279cc821b542e8946d50f8e4e77288ba654556300f7458016af8e83a4ba7","observation_id":"65f74ff7-2bd2-47d6-a87c-ec60543c3e75","resolution":{"observed_at":"2026-08-07T13:05:51.868173Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:51.674550Z","title":"Advanced mathematical methods for scientists and engineers I: Asymptotic methods and perturbation theory","venue":null,"work_id":"3f80b0ca-1876-4001-9c89-570ed71bbe2c","year":2013},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:43.123068Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:b4d626ebcdd9a7352a8b2e8cfc96ba6ae9b436c78ae8b32efb121a60836ac412","observation_id":"9e23c1e4-5cf0-46bd-8135-196df0035f56","resolution":{"observed_at":"2026-08-07T13:05:51.727878Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:51.509288Z","title":"Dynamical regimes of diffusion models","venue":null,"work_id":"b11b542e-7f76-4b0d-a66a-c58b03dfa1a3","year":2024},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:43.191590Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:7d826a61ea2a9b563d3b62b1357eeb45a91cfd190f6cf422b2bf0822ef5be6b3","observation_id":"218a6ac0-f04c-41c9-99a4-957647ea85e0","resolution":{"observed_at":"2026-08-07T13:05:51.608115Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:51.376989Z","title":"Shallow diffusion networks provably learn hidden low-dimensional structure","venue":null,"work_id":"9ca85421-8653-4786-8c38-81697fbb02c5","year":2025},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:43.237877Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:01f827a1c78dc623c70992910919b8c85729be8e3822fd1fe2c34e4ecb52d621","observation_id":"0b2fbd20-765a-4b36-8ddf-b5187d6b9074","resolution":{"observed_at":"2026-08-07T13:05:51.432907Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:51.254690Z","title":"Swarm gradient dynamics for global optimization: the mean-field limit case","venue":null,"work_id":"95e844ea-29ec-4de1-81d1-e153f85b6143","year":2024},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:43.331352Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:274d5758042355c8399259db5ceceb331a2d3f5016eeb3740418b8403389c2db","observation_id":"b7ed41c5-eab5-40c3-9ab2-39ae3a0b6934","resolution":{"observed_at":"2026-08-07T13:05:51.336232Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:51.096508Z","title":"Extracting training data from diffusion models","venue":null,"work_id":"3f58dc19-253a-47fb-8111-d427efbd32cc","year":2023},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:43.406253Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:1bb0c11e70ffd24e3a7ce4798f2c070c6527c68977d6a99774e3468a7be795a0","observation_id":"87eeb391-cb2c-4c8b-8f08-ce45d24222a8","resolution":{"observed_at":"2026-08-07T13:05:51.171970Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:50.940185Z","title":"Towards memorization-free diffusion models, 2024","venue":null,"work_id":"09a96cf2-e5ff-4fba-9903-ba0e9d06ae3a","year":2024},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:43.475063Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:4679a283c0bfde7444fe4c305c06554314379fe60144fb7f47c6168549e6f506","observation_id":"6a2971a2-3de0-4fcc-876e-e850313dc8e6","resolution":{"observed_at":"2026-08-07T13:05:51.024661Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:50.821884Z","title":"Improved analysis of score-based generative modeling: user-friendly bounds under minimal smoothness assumptions","venue":null,"work_id":"cdc3aa20-83e5-4485-95e8-382f7b55b53f","year":2023},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:43.542672Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:55dda94a1b227e6b483fba330d92f69fca7a75f94ddce61cc7191079f7410288","observation_id":"ca8372ca-e14e-41db-b5ee-2cb05954f4fe","resolution":{"observed_at":"2026-08-07T13:05:50.850232Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:50.654983Z","title":"Score approximation, estimation and distribution recovery of diffusion models on low-dimensional data","venue":null,"work_id":"120a788c-6ec2-49fe-b698-c0d197e00f1a","year":2023},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:43.580823Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:bcd478e56ef18791703cd352d897a2064b57103d18bd5c66da26a87debddf415","observation_id":"958af38c-c3cd-46fd-be09-8628ec70fb74","resolution":{"observed_at":"2026-08-07T13:05:50.748099Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:50.547120Z","title":"On the interpolation effect of score smoothing, 2025","venue":null,"work_id":"e7f21d3c-f648-42a3-92e3-f59690cf21ff","year":2025},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:43.679056Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:73e5bf8f2e7b23d2059887787f9cb7fa3283de1e0fb29d3545d7f0b1f676a9ba","observation_id":"3492b031-825f-4609-87af-ce5472781819","resolution":{"observed_at":"2026-08-07T13:05:50.618304Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:50.356092Z","title":null,"venue":null,"work_id":"e433f855-9a8e-41ec-a4b0-b0d2339edd45","year":2025},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:43.829006Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:d6d010949df2ec6bc2f72f9819b405849b3017d91db588d4c93f2aa2a203871a","observation_id":"85bf3479-2dd2-4184-a783-6aeec631ee62","resolution":{"observed_at":"2026-08-07T13:05:50.443885Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:50.218567Z","title":"Ambient diffusion: Learning clean distributions from corrupted data","venue":null,"work_id":"c91a95e2-2caa-4a1f-a7d5-0bb608c0e74c","year":2023},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:43.914256Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:fbc378326953792dea467a3fa18a99b79f577c2e5550a1109a0f6672d8c341a5","observation_id":"05dc69d4-ceea-4c36-a35e-46885239542f","resolution":{"observed_at":"2026-08-07T13:05:50.284618Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:50.034103Z","title":"Analysis of diffusion models for manifold data, 2025","venue":null,"work_id":"457cbbeb-4c76-491a-9387-6a077f5a187b","year":2025},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:44.011113Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:ef27fe5097362633312da9e1f18209f858c4147fef3d80bdf7001c6015f402ad","observation_id":"b39d3f66-aaf4-4132-874b-b2d84bbaaf58","resolution":{"observed_at":"2026-08-07T13:05:50.099455Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:49.838222Z","title":"On memorization in diffusion models","venue":null,"work_id":"8451bf7a-3925-4d9d-842a-e20dfe1d246f","year":2025},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:44.095219Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:d7b34de9787ebf52a0f775e0e18704ab9a3b40059766ceebcf2db0294653c84d","observation_id":"fa2752a6-47e8-4755-b4dd-a669d74a8f14","resolution":{"observed_at":"2026-08-07T13:05:49.931373Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:49.694795Z","title":"Linear Methods for Regression, pages 43–99","venue":null,"work_id":"0c864cc8-29cd-4b2c-92e3-573c6d6c7ab2","year":2009},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:44.176476Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:211e165d8d11ce6a892fc6442a4b60dc85cc20ddeafbdc5783f09c964dfc1da7","observation_id":"763b295c-0105-4355-a127-15eb88c5d4c8","resolution":{"observed_at":"2026-08-07T13:05:49.737669Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:49.516376Z","title":"Classifier-free diffusion guidance, 2022","venue":null,"work_id":"f5c0391c-0b6e-4913-9367-ea50399febdc","year":2022},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:44.267780Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:78a35e9cd0bda5311420ce58825cc5f4a0ed18b11c22017fa54f6a87fb200eba","observation_id":"89f8bead-cbb8-4a11-9f31-7753f553bfc3","resolution":{"observed_at":"2026-08-07T13:05:49.614022Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:49.353935Z","title":"Neural tangent kernel: Convergence and generalization in neural networks","venue":null,"work_id":"82e1d5a5-8538-4d27-89c2-cb098b751129","year":2018},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:44.354423Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:1af6f5702bedb7a63fee2576c97ab4ff1db1cf699e6daec93cf60a971400809f","observation_id":"9aacc366-858d-467c-ad8d-bc89f594f058","resolution":{"observed_at":"2026-08-07T13:05:49.416630Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:49.181690Z","title":"The variational formulation of the fokker– planck equation","venue":null,"work_id":"3a47741f-7060-43e8-8ff9-deb600ffb528","year":1998},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:44.426938Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:806e2c8a674e215bb016b4f915993386b7e84621ae50a0f02da846edbeadd8d9","observation_id":"370c4be2-70c3-4605-8d93-e8f0c1ef1150","resolution":{"observed_at":"2026-08-07T13:05:49.285362Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:48.996884Z","title":"Generalization in diffusion models arises from geometry-adaptive harmonic representation","venue":null,"work_id":"f61cec58-56aa-420f-8ac5-1d47ac316073","year":2024},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:44.482158Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:fdea706d8dc75470ae7306c171d9d8ba78f8233899294c8421d3165479cbe915","observation_id":"c2d3157e-7178-4df3-97d5-171c8eca7d40","resolution":{"observed_at":"2026-08-07T13:05:49.070690Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:48.823813Z","title":"An analytic theory of creativity in convolutional diffusion models, 2024","venue":null,"work_id":"c5def088-444e-4905-bfb9-38650c2520c4","year":2024},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:44.544949Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:2dd515eb48f6e8ddfbbc5ad6cd231894bc33b7e1481603584056f71326e1e2c0","observation_id":"65022b9b-0fec-4a12-aecc-dfa17c7fb22e","resolution":{"observed_at":"2026-08-07T13:05:48.886578Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:48.638873Z","title":"Wide neural networks of any depth evolve as linear models under gradient descent","venue":null,"work_id":"6eac5941-bdc7-404a-aa17-1d1c331c9142","year":2019},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:44.621865Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:438e830ec5590b73b9c3102886e2115ad06fe1b124d5d54d76cae11a272e0e8d","observation_id":"d0e42b3c-67cc-4a17-9078-cc209d5aca0f","resolution":{"observed_at":"2026-08-07T13:05:48.711963Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:48.453324Z","title":"On the generalization properties of diffusion models","venue":null,"work_id":"ba979c87-564c-40ba-8c4e-ba698593b409","year":2023},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:44.723304Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:8b3693323d82c7aa5a7547567271d89c36bb033bf0c0c6b1ed320f2d9b084d90","observation_id":"a185e9c0-e23c-48b0-bdd4-8e5bee3f5a5c","resolution":{"observed_at":"2026-08-07T13:05:48.533513Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:48.255456Z","title":"Understanding generalizability of diffusion models requires rethinking the hidden gaussian structure","venue":null,"work_id":"434f5823-6775-4a52-8964-341513724e4f","year":2024},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:44.816735Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:b9fd364212890d6c109e6f950004f1c0b8ebf9a5eeca787588eff191d8da6c41","observation_id":"c07c3009-e855-4ade-8137-29a04c56004c","resolution":{"observed_at":"2026-08-07T13:05:48.331096Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:48.076515Z","title":"Understanding diffusion models: A unified perspective, 2022","venue":null,"work_id":"f44cf638-ac5d-4418-80d3-77c83d431b70","year":2022},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:44.915161Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:b6fa1feb8ae62a5671f2abe5c99d6de1c3d0381769f01771858d30bd5aaf2ea9","observation_id":"ac123af3-36b0-442f-a9c2-bcb7cb41a356","resolution":{"observed_at":"2026-08-07T13:05:48.189773Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:47.926357Z","title":"Accelerating diffusion models via early stop of the diffusion process, 2022","venue":null,"work_id":"20f7fc1c-e7b5-42e6-8bc4-a6b26c72bfd5","year":2022},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:44.974488Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:cc0183ef207e5be5f3915088d6ac69dcea9cf17e784e7f4df909405d3834bb21","observation_id":"06be275d-5832-4d4e-9b69-23a0bc632fe4","resolution":{"observed_at":"2026-08-07T13:05:47.996461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:45.051353Z","title":null,"venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:45.051353Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:bc70cb481fb33b38893a222ab244541edf909f892436d8549cbf52559b0b4a76","observation_id":"23127625-1437-4e80-8f13-f2f7adade312","resolution":{"observed_at":"2026-08-07T13:05:45.051353Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:47.799320Z","title":null,"venue":null,"work_id":"cac9316a-3f34-4603-b3a6-f394a3692b55","year":1992},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:45.142125Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:0ab4f2179fbbec4e5348710e16fd50354e362d05975bdef2eb4edc6310d41ee6","observation_id":"35f74563-ace1-48d0-9002-5e96a23d1b89","resolution":{"observed_at":"2026-08-07T13:05:47.840901Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:47.632025Z","title":"U-net: Convolutional networks for biomedical image segmentation","venue":null,"work_id":"28df7567-15c6-47c0-adec-f98156ee8a86","year":2015},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:45.187954Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:8ebac478f9b76d1cc5c8edf88d28211592cd570cf57274c7c5c8bdfb44cccdc2","observation_id":"029fea84-6345-42fa-80ac-7f3a28d26eaa","resolution":{"observed_at":"2026-08-07T13:05:47.702831Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:47.496668Z","title":"Closed-form diffusion models, 2025","venue":null,"work_id":"e5dc37e5-d255-417a-8b30-2e7b0084c22a","year":2025},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:45.297810Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:ff78c00647228dc28fe234475289a4d1c70111753364784db61548949f24db72","observation_id":"2a120886-5926-436d-89b0-3d51f48fcfc0","resolution":{"observed_at":"2026-08-07T13:05:47.581256Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:47.396929Z","title":"Deep unsupervised learning using nonequilibrium thermodynamics","venue":null,"work_id":"f49857f0-c469-4d97-b366-b884ea6b34fd","year":2015},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:45.378265Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:f143e8132e7df74aa76719b21a6aca1957115c018c8237eed046c26430f4d7d6","observation_id":"ee8198d1-13d2-4a47-8e22-acd9abf6d145","resolution":{"observed_at":"2026-08-07T13:05:47.421888Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:45.443482Z","title":"Diffusion art or digital forgery? investigating data replication in diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:45.443482Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:f575a1e5a285306c3ff9cac927ace6a801a2f3968d811c7ed76da511b25522ed","observation_id":"94643512-04eb-48b5-bff5-b9af492054cc","resolution":{"observed_at":"2026-08-07T13:05:45.443482Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.20086","last_updated":"2023-05-31T17:58:02Z","snapshot_observed_at":"2026-08-14T01:47:12.308526Z","submitted_at":"2023-05-31T17:58:02Z","title":"Understanding and Mitigating Copying in Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.20086","snapshot_observed_at":"2026-08-07T13:05:45.487623Z","title":"Understanding and mitigating copying in diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:45.487623Z"},"links":{"cited_paper":"/paper/2305.20086","citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:e14878218cb90064005f4e8ef3e9c01ae7781c02c5381ab0809a70d026d82f4b","observation_id":"f391f5bf-92a4-4924-afbe-f4a7b5595414","resolution":{"observed_at":"2026-08-07T13:05:45.487623Z","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":"2026-08-07T13:05:45.575705Z","title":"Score-based generative modeling through stochastic differential equations","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:45.575705Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:f1efe97d8f915e0c0f3fa0ecd0c4a3b8d9f47313f3a6ab5b4408591a8cebe124","observation_id":"86a2c1e9-dd0b-44b9-89f7-f921a0d093d2","resolution":{"observed_at":"2026-08-07T13:05:45.575705Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:47.249999Z","title":"An analysis of the noise schedule for score-based generative models, 2025","venue":null,"work_id":"65ed0a49-9975-40ae-81f3-786c0c3c911f","year":2025},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:45.618410Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:8cc3dd08449e5230afbd03741579c83c51896640e68db3f22ebc156a5b08d561","observation_id":"ce3c4706-ec36-41ea-9a49-3a9d1a4ba02a","resolution":{"observed_at":"2026-08-07T13:05:47.299115Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:47.129880Z","title":"Regularization can make diffusion models more efficient, 2025","venue":null,"work_id":"13130d6c-a597-47fd-a571-5d65d1c24131","year":2025},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:45.679070Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:2a028480a4e8ed7f0385c2d4457832830136c82f00fa6f8cd4aaf4f3af101f98","observation_id":"b98771cd-bd2d-462c-979a-710184a75fcf","resolution":{"observed_at":"2026-08-07T13:05:47.173354Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:46.974949Z","title":"On memorization in probabilistic deep generative models","venue":null,"work_id":"ad727a4e-4f80-4d66-b71f-7bcd0b816854","year":2021},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:45.752084Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:6bfbce49cc5785c8d5af926557708c664febbd91c74b9d7cef0b8e3512b910a9","observation_id":"5987086b-137a-46ef-b7d5-f4f27d68ce76","resolution":{"observed_at":"2026-08-07T13:05:47.051673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:46.861761Z","title":"Manifolds, random matrices and spectral gaps: The geometric phases of generative diffusion","venue":null,"work_id":"3f6a1c9a-9d5a-446a-aa12-64518a84bc24","year":2025},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:45.812956Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:cc9541e3551717857f4aa07ef3901578824df043a101a58ad717204d0484c9bf","observation_id":"a92b0389-1732-4e94-b1a8-6f7931624633","resolution":{"observed_at":"2026-08-07T13:05:46.892994Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:46.721678Z","title":"Otto calculus, pages 421–433","venue":null,"work_id":"c3edc459-7b0d-42a3-b7bd-c012008e8dae","year":2009},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:45.902632Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:ce2299c1345936157e0c4bba5d7d5ecea3c710f3dc15968930345152eda0593d","observation_id":"9b05b71b-de6b-4d96-9f4a-3901e7cbd1ee","resolution":{"observed_at":"2026-08-07T13:05:46.774425Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:45.962322Z","title":"A connection between score matching and denoising autoencoders","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:45.962322Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:7d0bc89e601bf1b333308a491ecbba823b6ef9a21c694e0f7a35ca1fba81cb21","observation_id":"a67e4e9e-00db-429d-ba7a-82d1f9a5329f","resolution":{"observed_at":"2026-08-07T13:05:45.962322Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:46.570184Z","title":"Optimal score estimation via empirical bayes smoothing, 2024","venue":null,"work_id":"8ddda8fe-3a85-4013-815e-939c16a8bbe0","year":2024},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:46.053604Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:b4eef38e137b4a7ddd9171161d5fc02e4a17387b495cd7e21837fc01c192a084","observation_id":"f85a8cc5-93b5-43cb-a100-29899de61c5b","resolution":{"observed_at":"2026-08-07T13:05:46.640099Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:46.428057Z","title":"On the generalization of diffusion model, 2023","venue":null,"work_id":"7131798f-3e20-4c88-a1e4-5f0b41ea5e1b","year":2023},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:46.093489Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:046fe841ee76bf288e9246d73726031496e3d969343298a044256e510a3ceb06","observation_id":"d1e1dbcf-ecc3-4302-8bbe-c0b35c336ba5","resolution":{"observed_at":"2026-08-07T13:05:46.468060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:05:46.287758Z","title":"Φ(1) N (t, x) Φ(0) N (t, x) − mt(x) # , √ N","venue":null,"work_id":"9231e45b-92bd-4d62-9178-f7ac012de0ad","year":2023},"citing_paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:46.193531Z"},"links":{"citing_paper":"/paper/2505.22841"},"observation_digest":"sha256:e94dae4b5da09eb5aa67726130bd64675158613bf28ca3857246311e90a2c3b0","observation_id":"e99f5227-9734-4ce7-8585-4dfb25744158","resolution":{"observed_at":"2026-08-07T13:05:46.373590Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.22841","last_updated":"2025-05-28T20:22:18Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-11T15:05:43.578104Z","submitted_at":"2025-05-28T20:22:18Z","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study"},"reference_resolution":{"displayed":45,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":7,"verified_exact":0,"verified_fuzzy":37},"total_outbound_references":45},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 2 inbound Pith citation observations for arXiv:2505.22841."}