{"as_of":"2026-08-18T14:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:21ddb4b2009ecb82ff2705953545e2f1cbb3b6075a9f04a78a7b1906fc6b375d","coverage":[{"denominator":61,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":61,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T12:36:32.203918Z","state":"measured"},{"denominator":64,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":64,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-11T07:46:49.059192Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-08T00:04:22.434986Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"cited_work":{"arxiv_id":"2504.12532","doi":null,"metadata_source":"pith","pith_arxiv_id":"2504.12532","snapshot_observed_at":"2026-07-08T00:04:22.434986Z","title":"2025 , month = apr, number =","venue":"cs.LG","work_id":"1333fcef-a6bc-4fc9-a70f-c8ba77103951","year":2025},"citing_paper":{"arxiv_id":"2605.10019","last_updated":"2026-05-11T05:44:18Z","snapshot_observed_at":"2026-08-16T08:48:37.559402Z","submitted_at":"2026-05-11T05:44:18Z","title":"The two clocks and the innovation window: When and how generative models learn rules","version":1},"reference_index":118,"source":"arxiv_source","source_observed_at":"2026-05-12T03:15:45.257213Z"},"links":{"cited_paper":"/paper/2504.12532","citing_paper":"/paper/2605.10019"},"observation_digest":"sha256:c1963f7073c7cdd2b52d0ea1380527a1b3b8c53bdf9a2b1d27ae12c72595c9bb","observation_id":"0a8785fe-c7c4-42d2-8638-5a10d9596446","resolution":{"observed_at":"2026-05-12T03:16:18.613801Z","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":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"cited_work":{"arxiv_id":"2504.12532","doi":null,"metadata_source":"pith","pith_arxiv_id":"2504.12532","snapshot_observed_at":"2026-07-08T00:04:22.434986Z","title":"2025 , month = apr, number =","venue":"cs.LG","work_id":"1333fcef-a6bc-4fc9-a70f-c8ba77103951","year":2025},"citing_paper":{"arxiv_id":"2607.05196","last_updated":"2026-07-07T15:36:48Z","snapshot_observed_at":"2026-08-13T19:24:37.674798Z","submitted_at":"2026-07-06T15:11:57Z","title":"Unified Audio Intelligence Without Regressing on Text Intelligence","version":1},"reference_index":169,"source":"arxiv_source","source_observed_at":"2026-07-07T23:59:38.702609Z"},"links":{"cited_paper":"/paper/2504.12532","citing_paper":"/paper/2607.05196"},"observation_digest":"sha256:4718f5f47547961f09bcab2ab0f9e7d221ae3ee042869163fbe939e9dd39848b","observation_id":"70963400-72a4-41d4-9d85-843505e3352d","resolution":{"observed_at":"2026-07-08T00:04:22.436409Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"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":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.12532","snapshot_observed_at":"2026-07-11T07:46:49.059192Z","title":"arXiv preprint arXiv:2504.12532 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.05196","last_updated":"2026-07-07T15:36:48Z","snapshot_observed_at":"2026-08-13T19:24:37.674798Z","submitted_at":"2026-07-06T15:11:57Z","title":"Unified Audio Intelligence Without Regressing on Text Intelligence","version":2},"reference_index":169,"source":"arxiv_source","source_observed_at":"2026-07-11T07:46:49.059192Z"},"links":{"cited_paper":"/paper/2504.12532","citing_paper":"/paper/2607.05196"},"observation_digest":"sha256:f34125cc4f3148919dd8dec641634af1b799e1525ef9b91e806aee7cf14fbee9","observation_id":"2d17c73f-951f-4dc1-b364-b0890ca577a5","resolution":{"observed_at":"2026-07-11T07:46:49.059192Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2504.12532/citation-record","integrity":"/paper/2504.12532/integrity","json":"/paper/2504.12532/citation-record.json","paper":"/paper/2504.12532"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:36:31.978413Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:31.978413Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:256d5b2a1305d0be9547cc4406f429b21ce84a9488611313a7f55a7566688259","observation_id":"c8274703-abee-4bfa-bbc8-686694e7b9a2","resolution":{"observed_at":"2026-08-16T12:36:31.978413Z","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":"2026-08-16T12:36:33.120857Z","title":"On exact computation with an infinitely wide neural net","venue":null,"work_id":"0474e5d5-4c21-45e0-b3a8-5a609a8bb5c0","year":2019},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:31.983593Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:40b8c98d638b10fc4a17201073889bf11b541f2cf2434d86a0a5931ac1cefc91","observation_id":"aa88733b-b90f-4166-8a26-b7caaf56e0e7","resolution":{"observed_at":"2026-08-16T12:36:33.124401Z","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":"2026-08-16T12:36:33.109091Z","title":"On the inductive bias of neural tangent kernels","venue":null,"work_id":"5c550268-9ea4-47ca-8b0c-c676efc3a08f","year":2019},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:31.987368Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:711f290af0d35e59b33f587da9b8491098e0ab1e8ee37531d4e0659ef48fdebc","observation_id":"6f90ba21-04a2-429a-899c-70c025b62f47","resolution":{"observed_at":"2026-08-16T12:36:33.112835Z","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":"2026-08-16T12:36:33.097033Z","title":"Align your latents: High-resolution video synthesis with latent diffusion models","venue":null,"work_id":"d4c6b42d-c438-4ebb-a1c4-63f0e13cdcfb","year":2023},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:31.991443Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:13e8a5f1a83fa62763beca41bd306f58ca5cb9e76911585d5ac0afd130ec432e","observation_id":"fe463c13-8326-4623-8bb7-0d3020765663","resolution":{"observed_at":"2026-08-16T12:36:33.101019Z","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":"2026-08-16T12:36:33.084831Z","title":"Self-consistent dynamical field theory of kernel evolution in wide neural networks","venue":null,"work_id":"4f074115-90ff-41c7-94f3-063ca6e72f04","year":2022},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:31.995232Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:2316ebc18358d7726088c604e0fccabcc7f6077e09f37941e4c304569922539c","observation_id":"e8b0ec26-7315-45b4-a716-034b8dafe2d4","resolution":{"observed_at":"2026-08-16T12:36:33.088664Z","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":"2026-08-16T12:36:31.999008Z","title":"Self-consistent dynamical field theory of kernel evolution in wide neural networks*","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:31.999008Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:2b57ce983173efdd0e52c9b669b78d2633abf6188436683e4105a25e627250f6","observation_id":"4fc4060e-6c58-491c-b73b-f0007b82319a","resolution":{"observed_at":"2026-08-16T12:36:31.999008Z","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":"2026-08-16T12:36:33.072572Z","title":"Spectrum dependent learning curves in kernel regression and wide neural networks","venue":null,"work_id":"53ae81d2-760d-43e4-803a-1fd87b0f54e6","year":2020},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.002827Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:a1d75a673bea56fa7202ddf566ad7268531eea4629bd2aa97babf5489b6245b4","observation_id":"ebc9d33e-570b-4e60-9630-a2375f357a64","resolution":{"observed_at":"2026-08-16T12:36:33.076480Z","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":"2026-08-16T12:36:33.059888Z","title":"Convergence of denoising diffusion models under the manifold hypothesis","venue":null,"work_id":"f38e6619-8a24-4337-9bf1-144d5a8b0daa","year":2022},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.007051Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:804310c63d9da805c5c6fc5e78aa6c21bcfe4171ad47c9bac7e2e041e869f924","observation_id":"39ed3161-37b2-46ee-806e-439ac1c95043","resolution":{"observed_at":"2026-08-16T12:36:33.063839Z","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":"2026-08-16T12:36:33.046538Z","title":"Diffusion schr\\\"odinger bridge with applications to score-based generative modeling","venue":null,"work_id":"2b8863f7-d607-49b3-919c-99f0dea4013d","year":2021},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.010620Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:5ac010c611853ddc529ec598b911fc9d63d56a87c3fefd04f1d2b3d70bf78250","observation_id":"3ad6df46-86d3-4aa6-a0bf-f219f4cc6c54","resolution":{"observed_at":"2026-08-16T12:36:33.051003Z","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":"2026-08-16T12:36:32.014168Z","title":"Spectral bias and task-model alignment explain generalization in kernel regression and infinitely wide neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.014168Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:fbbc4eab2224b745456f251e942a9553a3342fcd07a446f1d8ec0ec0750bfe54","observation_id":"63a34561-115d-45df-a98d-d8cb9e3a4f06","resolution":{"observed_at":"2026-08-16T12:36:32.014168Z","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":"2026-08-16T12:36:33.033384Z","title":"Extracting training data from diffusion models","venue":null,"work_id":"f879a4ec-2f00-4229-82d0-8571b281e7fa","year":2023},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.017977Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:de15664c04e3de7eec3821204dfdbc68247f6a1f5820f383658e39ed6053c05b","observation_id":"54b6f331-a12e-42b2-9e9e-e3e42cc0f612","resolution":{"observed_at":"2026-08-16T12:36:33.037305Z","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":"2026-08-16T12:36:33.020861Z","title":"Denoising likelihood score matching for conditional score-based data generation","venue":null,"work_id":"0d194c66-d957-45b2-a1ab-8d0dbc95182c","year":2022},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.022215Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:aaceedc16f1823170357632a3ec6605009305bf4b5c2ac339f51e0cf525ca911","observation_id":"1525416d-57a6-4a3f-bf94-d1d42eb9d526","resolution":{"observed_at":"2026-08-16T12:36:33.024691Z","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":"2026-08-16T12:36:33.008470Z","title":"Score approximation, estimation and distribution recovery of diffusion models on low-dimensional data","venue":null,"work_id":"26a7be7f-b6b8-4de1-bfdb-67dd45159791","year":2023},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.025777Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:8fec35d368ef5d1fc3e617e2d196549c6d6f39938f94889c16c26d2c4343cdf0","observation_id":"3663ac8f-5bf2-4969-a9bb-106be6a9695b","resolution":{"observed_at":"2026-08-16T12:36:33.012528Z","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":"2026-08-16T12:36:32.995656Z","title":null,"venue":null,"work_id":"007521e0-6227-4b94-b122-31620da58393","year":2018},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.029298Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:afb04df12d22c3f249cbf00c2e183b7cb113ce3b11e5cbffb67e9638e43f0422","observation_id":"a67dfc0f-9a75-4968-a7d1-3e84008b3c48","resolution":{"observed_at":"2026-08-16T12:36:32.999764Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-16T12:36:32.982901Z","title":"The probability flow ode is provably fast","venue":null,"work_id":"6f7e9431-5a3c-4937-a232-34bc9defd73c","year":2023},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.032885Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:67f4b97d1de975bd358e793d30ee61309ad83bd6bc82ae4b6fb2eb4dd641f00d","observation_id":"8d31e85c-09b0-424a-8efb-6df9f33d811c","resolution":{"observed_at":"2026-08-16T12:36:32.986896Z","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":"2026-08-16T12:36:32.036436Z","title":"Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.036436Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:3e2c8e99728198a8dc9825127c770aa8e774c0f4f4131970f8848256f92021e2","observation_id":"97b5fffa-3ad4-4b21-9faf-5b640a76e8c9","resolution":{"observed_at":"2026-08-16T12:36:32.036436Z","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":"2026-08-16T12:36:32.960911Z","title":"On lazy training in differentiable programming","venue":null,"work_id":"9a253f83-897c-49b5-93da-c5e0f9fa3718","year":2019},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.040376Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:411774886456b0fc7b662bcf1d798465e1a74f546f42bd13d2c26717514e4eaa","observation_id":"014c9490-1a84-47cc-a6cc-23cb9e98a1d7","resolution":{"observed_at":"2026-08-16T12:36:32.964815Z","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":"2026-08-16T12:36:32.948637Z","title":"Group equivariant convolutional networks","venue":null,"work_id":"8b35c34f-a799-4c54-85f8-bb674f350a85","year":2016},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.044012Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:edae2303820b7b0f56b92b048cb3cf8b8214a92974d288bc747c65598b0f35a5","observation_id":"6799b5fa-61bf-4e00-ac07-c7bd5abf6c9d","resolution":{"observed_at":"2026-08-16T12:36:32.952582Z","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":"2026-08-16T12:36:32.047844Z","title":"Crisanti and H","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.047844Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:4d34b7f7b6bd4118fa18e7a5f35a98a0c351d5239948f07fdd6e2fc78bed8924","observation_id":"f9736004-d03a-4917-8c62-95c4dd389a1c","resolution":{"observed_at":"2026-08-16T12:36:32.047844Z","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":"10.1007/978-3-031-53767-7_6","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-17T11:03:46.409680Z","title":"Schoenberg, and Sandy Engelhardt","venue":"Lecture notes in computer science","work_id":"7504f82a-693d-4c4f-bf57-87c815ee2651","year":2023},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.052549Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:352d25e9b91520fb44201426a7d7c160e781a73b7e24f5f292be5895f5ca8d27","observation_id":"53472a42-b190-42c8-a426-8f970dedb469","resolution":{"observed_at":"2026-08-16T12:36:32.294622Z","resolver_source":"doi","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":"2026-08-16T12:36:32.935366Z","title":"GENIE : Higher-order denoising diffusion solvers","venue":null,"work_id":"a3fc02e8-740a-40f1-8e2f-70bce99dec97","year":2022},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.056242Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:5669b1a2ee477b4b87cbf6541a7f883334a2268b621aceacf95289bc1a8b31e2","observation_id":"be25bdde-721c-438e-8304-fab76872d747","resolution":{"observed_at":"2026-08-16T12:36:32.939926Z","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":"2026-08-16T12:36:32.923129Z","title":"Score-based generative modeling with critically-damped langevin diffusion","venue":null,"work_id":"8da7cdf7-2333-45da-8504-ae9c5f132f35","year":2022},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.059948Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:918405763d80dd72bf32a5cb5afb68a66782dd822ca576e9282e61432b90c620","observation_id":"27afff57-7d96-4f8f-b232-54b65707d0d1","resolution":{"observed_at":"2026-08-16T12:36:32.926939Z","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":"2026-08-16T12:36:32.063421Z","title":"Disentangling feature and lazy training in deep neural networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.063421Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:caf96419cd59bd559ab7fe533f2364a60420eaa9042322923f6ebf25374f39e3","observation_id":"0540f058-0077-4dc8-9528-6ce74284a0d0","resolution":{"observed_at":"2026-08-16T12:36:32.063421Z","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":"2026-08-16T12:36:32.910665Z","title":"Neural network-based score estimation in diffusion models: Optimization and generalization","venue":null,"work_id":"7fd53a8d-6695-4b8c-bda4-335de7e0d4d2","year":2024},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.067109Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:b165b54f27047ceb172edece32d2cc0c068e1852328a4d635e9cfba4c6d42669","observation_id":"40439d89-99c1-43a5-b5c3-5ee8fd9e72db","resolution":{"observed_at":"2026-08-16T12:36:32.914636Z","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":"2026-08-16T12:36:32.070720Z","title":"Denoising diffusion probabilistic models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.070720Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:b89ec465fe5a9afe30a40a9cdae8da0cb601e7965ec109c9dbd51f3cdfdfb5b0","observation_id":"10ef5f32-be2e-4191-9d5d-3fa96c8fab06","resolution":{"observed_at":"2026-08-16T12:36:32.070720Z","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":"2026-08-16T12:36:32.888562Z","title":"Neural tangent kernel: Convergence and generalization in neural networks","venue":null,"work_id":"f194ec87-69f0-4c1a-a1a2-0d07cb8399ec","year":2018},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.074252Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:3c2d1a55146fb3aaa7a1c7a81a5ae3dd5f0a93c8aab82ef8eca981d288dc4b11","observation_id":"09f7a0ff-d0f0-4011-8b69-edb4d2bb8b1d","resolution":{"observed_at":"2026-08-16T12:36:32.892598Z","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":"2026-08-16T12:36:32.077736Z","title":"Generalization in diffusion models arises from geometry-adaptive harmonic representations","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.077736Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:fa624223305363dbf19685b10a4a596c9cc7a03313b60938f4d507e6ee181512","observation_id":"182f67c1-6426-43b6-a52d-59043075d867","resolution":{"observed_at":"2026-08-16T12:36:32.077736Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.20292","last_updated":"2025-06-05T05:09:27Z","snapshot_observed_at":"2026-08-16T08:43:12.375693Z","submitted_at":"2024-12-28T22:33:29Z","title":"An analytic theory of creativity in convolutional diffusion models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.20292","snapshot_observed_at":"2026-08-16T12:36:32.081606Z","title":"An analytic theory of creativity in convolutional diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.081606Z"},"links":{"cited_paper":"/paper/2412.20292","citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:38433fda1909691bcf7c0e57a75ae4b2f15bea1f666905d8cd78a412195779bc","observation_id":"8859bc1a-94c2-4fb7-a10d-e3da8583f9ae","resolution":{"observed_at":"2026-08-16T12:36:32.081606Z","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":"2026-08-16T12:36:32.085992Z","title":"Elucidating the design space of diffusion-based generative models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.085992Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:b11ae21339d9d6bfb535cf62bd6ac94cc536fe7d1be354cee8f1e6be37ac5dde","observation_id":"537176d1-4cf8-463e-b8bb-3c54a1021145","resolution":{"observed_at":"2026-08-16T12:36:32.085992Z","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":"2026-08-16T12:36:32.089595Z","title":"Analyzing and improving the training dynamics of diffusion models, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.089595Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:badd1726aa92196b775632d0eaa0fe6052e0f6d3574cf24273e8715a0600eb09","observation_id":"b15d6491-5319-421f-9a88-80ea46a53542","resolution":{"observed_at":"2026-08-16T12:36:32.089595Z","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":"2026-08-16T12:36:32.850075Z","title":"Path integrals in quantum mechanics, statistics, polymer physics, and financial markets","venue":null,"work_id":"199d8c4a-be18-44b7-83c1-12802f4ace78","year":2006},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.093242Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:bb1ed9b5c4d3795fe4a5021e3f5185d7882ca23daa5d6995f86dcddc72a28de0","observation_id":"aa2e14f5-9e56-4742-9434-552d4817387b","resolution":{"observed_at":"2026-08-16T12:36:32.854272Z","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":"2202.09778","last_updated":"2022-10-31T09:05:25Z","snapshot_observed_at":"2026-08-16T17:20:02.890207Z","submitted_at":"2022-02-20T10:37:52Z","title":"Pseudo Numerical Methods for Diffusion Models on Manifolds","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.09778","snapshot_observed_at":"2026-08-16T12:36:32.096879Z","title":"Pseudo numerical methods for diffusion models on manifolds","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.096879Z"},"links":{"cited_paper":"/paper/2202.09778","citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:1c4f3de93b4c41966214128050ac07b60f2242a3a7a6ef46831a72f141704aef","observation_id":"e66f6f4d-b1a3-4b17-8baa-3a85568a54ce","resolution":{"observed_at":"2026-08-16T12:36:32.096879Z","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":"2026-08-16T12:36:32.836896Z","title":"Boomerang: Local sampling on image manifolds using diffusion models","venue":null,"work_id":"0d88985d-a8b6-4d9a-8154-c68685bdd0fa","year":2024},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.100792Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:56716a7cb5eb64009498012b5e692361b20441c55a6aca67be7138f2aa8d83bc","observation_id":"8889c140-a60e-44c3-9fe3-85df3dc54c5b","resolution":{"observed_at":"2026-08-16T12:36:32.840967Z","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":"2026-08-16T12:36:32.103997Z","title":null,"venue":null,"work_id":null,"year":1973},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.103997Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:bbc0b1b2188ce89cddcd9057dd2306933e8f5a90805c01f3fca6d57dd8cb7646","observation_id":"f791826a-8e9c-4121-b9e4-96f8cf5a95e5","resolution":{"observed_at":"2026-08-16T12:36:32.103997Z","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":"2026-08-16T12:36:32.823762Z","title":"Dynamical mean-field theory for stochastic gradient descent in gaussian mixture classification","venue":null,"work_id":"6b139253-d298-48c4-aa2e-e863d164292b","year":2020},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.107581Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:eb812e3ef7a9b888bcf983855ab3b56872f5cf28065a34f5d9b5969f1a8156d3","observation_id":"26370540-b800-4662-a4ef-4fc310ec194a","resolution":{"observed_at":"2026-08-16T12:36:32.828040Z","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":"2411.19339","last_updated":"2025-06-09T18:57:55Z","snapshot_observed_at":"2026-08-13T07:38:24.430863Z","submitted_at":"2024-11-28T19:22:17Z","title":"Towards a Mechanistic Explanation of Diffusion Model Generalization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.19339","snapshot_observed_at":"2026-08-16T12:36:32.111072Z","title":"Towards a mechanistic explanation of diffusion model generalization","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.111072Z"},"links":{"cited_paper":"/paper/2411.19339","citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:fb3f561c70c9b4eff47c36533704716d890c5908d1d9e5b12891e6815ff772d6","observation_id":"fb0a68a9-a3d0-4faf-ac1c-51815939efc7","resolution":{"observed_at":"2026-08-16T12:36:32.111072Z","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":"2026-08-16T12:36:32.810960Z","title":"On the spectral bias of neural networks","venue":null,"work_id":"84f1d01b-6f57-452c-835b-49a3ad25f623","year":null},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.114827Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:9cc903ab003ef4263b928ecd698764e3be4d2728f206bca2ec25a9bed3c032e2","observation_id":"904253c7-eef3-4c00-aac4-a9247f043388","resolution":{"observed_at":"2026-08-16T12:36:32.815023Z","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":"2026-08-16T12:36:32.118604Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.118604Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:d7095adafc5f5d9411c095cc36ca3e045852884115348363dbe2378e87173472","observation_id":"e3e052d2-be24-4fb3-ab8b-93451e53b36e","resolution":{"observed_at":"2026-08-16T12:36:32.118604Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.14301","last_updated":"2022-02-10T01:39:58Z","snapshot_observed_at":"2026-08-16T18:21:14.206110Z","submitted_at":"2021-05-29T13:50:03Z","title":"A Theory of Neural Tangent Kernel Alignment and Its Influence on Training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.14301","snapshot_observed_at":"2026-08-16T12:36:32.122013Z","title":"A theory of neural tangent kernel alignment and its influence on training, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.122013Z"},"links":{"cited_paper":"/paper/2105.14301","citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:2fe28079b15a308f7245085bb5cf3d96128815e07725165cce9c6b78f329ad62","observation_id":"ee9135f8-4dc4-49d7-8027-9b03efc0a7cd","resolution":{"observed_at":"2026-08-16T12:36:32.122013Z","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":"2026-08-16T12:36:32.789360Z","title":"On the generalization benefit of noise in stochastic gradient descent","venue":null,"work_id":"811af741-034b-47b7-a5a4-9b0c01da6140","year":2020},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.125943Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:525307a6f67b0bee9d8673a8a2c3177d683225cb0ec7460155aa23b6d2a22a93","observation_id":"70769471-3637-42f8-8417-0aee91534098","resolution":{"observed_at":"2026-08-16T12:36:32.793416Z","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":"2026-08-16T12:36:32.776801Z","title":"Smith and Quoc V","venue":null,"work_id":"ddcdcafa-0c8b-4142-badc-ad2a7cc45cfa","year":2018},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.129421Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:b0c0d8285f604a2f0891eed68f941a7ca3f0dd6214a6e3f7d0beda4c055406f8","observation_id":"d2f81006-1200-491c-92d2-c99a9ac2435b","resolution":{"observed_at":"2026-08-16T12:36:32.780562Z","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":"2026-08-16T12:36:32.132928Z","title":"Deep unsupervised learning using nonequilibrium thermodynamics","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.132928Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:248558051b6ac9a29fffcb8382c6d900f531126d5a83cff724cc70c04ee7ca8a","observation_id":"02957564-0208-4c6c-97c0-10e2c87935d6","resolution":{"observed_at":"2026-08-16T12:36:32.132928Z","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":"2026-08-16T12:36:32.754758Z","title":"Diffusion art or digital forgery? investigating data replication in diffusion models","venue":null,"work_id":"362d2600-626a-4942-8647-87ddae386052","year":2023},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.136655Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:f8174da277bb678a6261a496a3d411ae6b891baacbf062edc78e051bb3c5a279","observation_id":"49a84cbf-5f7d-429a-8618-f12922de1290","resolution":{"observed_at":"2026-08-16T12:36:32.758978Z","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":"2026-08-16T12:36:32.741202Z","title":"Understanding and mitigating copying in diffusion models","venue":null,"work_id":"572f8544-fd07-4163-8822-e675d86c3052","year":2023},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.140620Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:fa1771583daa265d6ab5bc477eba04773d1d25a40233fe9b0e5aedf984bf6854","observation_id":"001d6421-b9e2-428b-b8b5-aaa7f25b3459","resolution":{"observed_at":"2026-08-16T12:36:32.745327Z","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":"2026-08-16T12:36:32.727772Z","title":"Generative modeling by estimating gradients of the data distribution","venue":null,"work_id":"5cafcccd-2fac-4f7e-8980-f0ac998bf096","year":2019},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.144285Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:7f0aa13d493c75a7f6e32035e5ef27c4676eb3de514d01a7fa00d6e84f040a70","observation_id":"6602a2b0-df07-495d-aa1d-491ca6b05848","resolution":{"observed_at":"2026-08-16T12:36:32.732086Z","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":"2026-08-16T12:36:32.713978Z","title":"Sliced score matching: A scalable approach to density and score estimation","venue":null,"work_id":"979f909c-69f9-46c7-997a-776f13aef59f","year":2020},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.147943Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:70b9fe0a9160ab49781fd6b9b9c17f3c8d458b3f0548e51e4cf2b66e20c514a6","observation_id":"1925080a-8b5c-4b07-b7a0-db06a37c4778","resolution":{"observed_at":"2026-08-16T12:36:32.718303Z","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":"2026-08-16T12:36:32.151738Z","title":"Score-based generative modeling through stochastic differential equations","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.151738Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:46bad4a3883e8841cfe72fc789881cc51979537a4be9d7448338094b49215eb1","observation_id":"93ded67d-21cc-4672-8ec2-f88d4f5e5cb3","resolution":{"observed_at":"2026-08-16T12:36:32.151738Z","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":"2026-08-16T12:36:32.690445Z","title":"Cresswell, Rasa Hosseinzadeh, Yi Sui, Brendan Leigh Ross, Valentin Villecroze, Zhaoyan Liu, Anthony L","venue":null,"work_id":"07045215-03f1-4413-9bba-ebdff49ae846","year":2023},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.155305Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:5e0fe591b4c37bc4cdd31fceae34af19f62d7b1dd53e9eca8a0a31a5c4f980b5","observation_id":"ea150992-c784-4111-b5f2-1ce90e19e738","resolution":{"observed_at":"2026-08-16T12:36:32.695128Z","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":"2026-08-16T12:36:32.159183Z","title":"A connection between score matching and denoising autoencoders","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.159183Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:6d57c6f327719fcf7e2adf8bc0ee630d2cc229fa5ca4e0bf190156e44ffffb13","observation_id":"8d6ff9f0-bbea-4af7-a25e-b6544677d9a6","resolution":{"observed_at":"2026-08-16T12:36:32.159183Z","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":"2026-08-16T12:36:32.676096Z","title":"Kakade, and Boaz Barak","venue":null,"work_id":"95015788-4bf8-441e-9fe7-c53bc5875e98","year":2023},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.162900Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:8408f1254f1b037c1ee339d31e4b57abea1968c277f9aeb0a0d561f876a50ac2","observation_id":"c27f54af-0cdf-4ec7-9428-3e40edf67e9b","resolution":{"observed_at":"2026-08-16T12:36:32.680189Z","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":"2026-08-16T12:36:32.662719Z","title":"The unreasonable effectiveness of gaussian score approximation for diffusion models and its applications","venue":null,"work_id":"50135095-7faf-4378-9525-5b8722ffd26a","year":2024},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.166471Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:ed8187f7c5e815c9d1e0250a952ebf07fc4660458a7409825eab79656f3ebb46","observation_id":"0f81ca1e-e7ca-4d88-b318-7a4d4e7d4ef0","resolution":{"observed_at":"2026-08-16T12:36:32.667057Z","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":"2303.02490","last_updated":"2024-03-26T03:41:26Z","snapshot_observed_at":"2026-08-16T15:50:47.894244Z","submitted_at":"2023-03-04T20:08:57Z","title":"Diffusion Models Generate Images Like Painters: an Analytical Theory of Outline First, Details Later","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.02490","snapshot_observed_at":"2026-08-16T12:36:32.170258Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.170258Z"},"links":{"cited_paper":"/paper/2303.02490","citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:92a07a7bb3bc87a6b0d9cc011c62859a97e24397cadcdd888b5263428c87050a","observation_id":"9bbe77fa-fb0e-45e2-9f93-a826e1c65cc5","resolution":{"observed_at":"2026-08-16T12:36:32.170258Z","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":"2026-08-16T12:36:32.649528Z","title":"Lee, Edward Moroshko, Pedro Savarese, Itay Golan, Daniel Soudry, and Nathan Srebro","venue":null,"work_id":"32e34dc7-4a48-465d-83f8-7ac36bdf5584","year":2020},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.174157Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:7494e4db0fb1337304b021ea2013969ef5e67932d2e9f09518f38539cee8df09","observation_id":"378e1b5b-f527-40b5-93dd-3df6d5361a3f","resolution":{"observed_at":"2026-08-16T12:36:32.653648Z","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":"2026-08-16T12:36:32.636383Z","title":"Jaakkola","venue":null,"work_id":"f47c7e62-acc4-4a17-84b8-c94a3a69e7e2","year":2023},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.177780Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:f3b31bfb69b76104fe10c47063867e0ba86f97d1632142d0381b8b03652f37d3","observation_id":"a1295ba5-151c-4ec0-9337-855ab0ce93af","resolution":{"observed_at":"2026-08-16T12:36:32.640360Z","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":"2026-08-16T12:36:32.181303Z","title":"Diffusion models: A comprehensive survey of methods and applications","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.181303Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:88eaf55f03e978fdb9ed2dec6dd8c7d40d327435d09c30bf635b7469cce3e520","observation_id":"292af853-4a02-4798-90f9-8b7a44a03418","resolution":{"observed_at":"2026-08-16T12:36:32.181303Z","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":"2026-08-16T12:36:32.623592Z","title":null,"venue":null,"work_id":"1b52a2ae-942f-43a7-b7d0-8554136c4440","year":2023},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.184966Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:0caad8a411db17d127bcf75dd4f86321a197842021661e31cc425528cd321469","observation_id":"b2570d8a-26a1-48b3-a842-b90e66dfbd90","resolution":{"observed_at":"2026-08-16T12:36:32.627480Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-16T12:36:32.188524Z","title":"Understanding deep learning requires rethinking generalization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.188524Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:0f15d334ac276bd44f2d326990579f8c255ac96a71ff61bd9a817cba25124abd","observation_id":"db01f84a-f1ec-4299-b7c4-ee58515f6c84","resolution":{"observed_at":"2026-08-16T12:36:32.188524Z","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":"2026-08-16T12:36:32.600073Z","title":"The emergence of reproducibility and consistency in diffusion models","venue":null,"work_id":"e0e92d04-b28c-4afe-b094-36a73cb3a022","year":2024},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.192088Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:b9f254fe82b2a87ca28ad21760107235b098df5e1f24ef1d6ec439ad3f688e58","observation_id":"150e60e9-8742-4158-9082-c0905cb0e727","resolution":{"observed_at":"2026-08-16T12:36:32.604862Z","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":"2026-08-16T12:36:32.195711Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.195711Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:4be5844e95bfb9c97ad32157c5c305eabc72061fd05fc20e552675ca205f6418","observation_id":"8f658099-6be7-45b0-ad0d-bf1af6fdd9df","resolution":{"observed_at":"2026-08-16T12:36:32.195711Z","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":"2026-08-16T12:36:32.200138Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.200138Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:665a85d532bb50817e23baf24aaf1eaba3172cc3007a83b59c14d7e50c4f7908","observation_id":"4baa620c-d588-49c4-a5d3-43b42fa2513d","resolution":{"observed_at":"2026-08-16T12:36:32.200138Z","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":"2084.68973","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T12:36:32.505672Z","title":"\" id=\"W5M0MpCehiHzreSzNTczkc9d","venue":null,"work_id":"b4422168-edb7-4391-9ed9-d2ac1c712091","year":2020},"citing_paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models","version":1},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-16T12:36:32.203918Z"},"links":{"citing_paper":"/paper/2504.12532"},"observation_digest":"sha256:01dcd148b667f7822f1050a56aea8699daed32cbb3c8c11b1193c886c8a64964","observation_id":"87a99d43-d7a1-4f80-a89c-135ed1e26c44","resolution":{"observed_at":"2026-08-16T12:36:32.512282Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"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"}}],"paper":{"arxiv_id":"2504.12532","last_updated":"2025-04-16T23:41:10Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T11:43:26.038936Z","submitted_at":"2025-04-16T23:41:10Z","title":"Generalization through variance: how noise shapes inductive biases in diffusion models"},"reference_resolution":{"displayed":61,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":26,"verified_exact":1,"verified_fuzzy":33},"total_outbound_references":61},"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 61 of 61 outbound references and 3 inbound Pith citation observations for arXiv:2504.12532."}