{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:37KLJGTDL455YSS3VLL3WBKIAK","short_pith_number":"pith:37KLJGTD","schema_version":"1.0","canonical_sha256":"dfd4b49a635f3bdc4a5baad7bb054802a518e1d79c0f5196b4f9b4aa9472ce48","source":{"kind":"arxiv","id":"2209.05557","version":3},"attestation_state":"computed","paper":{"title":"Blurring Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Emiel Hoogeboom, Tim Salimans","submitted_at":"2022-09-12T19:16:48Z","abstract_excerpt":"Recently, Rissanen et al., (2022) have presented a new type of diffusion process for generative modeling based on heat dissipation, or blurring, as an alternative to isotropic Gaussian diffusion. Here, we show that blurring can equivalently be defined through a Gaussian diffusion process with non-isotropic noise. In making this connection, we bridge the gap between inverse heat dissipation and denoising diffusion, and we shed light on the inductive bias that results from this modeling choice. Finally, we propose a generalized class of diffusion models that offers the best of both standard Gaus"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2209.05557","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-12T19:16:48Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"668f344b86509b417401b3bd583f95f985c3e0bbb2cc9ecc29eedd1fd4590292","abstract_canon_sha256":"3f6bad3c0498594b3693569532c4a463568e11dae89a3c7f9c3b5d4e5bc2eb59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:57.420127Z","signature_b64":"TpSrGwtf9D1S7AzE79uwVSNBLPyaLQBK4SA42KhIzLH/AynHMMWy9uSqlG+fZns19kLj/tbAeoKZw73ueqBfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfd4b49a635f3bdc4a5baad7bb054802a518e1d79c0f5196b4f9b4aa9472ce48","last_reissued_at":"2026-07-05T08:13:57.419670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:57.419670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Blurring Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Emiel Hoogeboom, Tim Salimans","submitted_at":"2022-09-12T19:16:48Z","abstract_excerpt":"Recently, Rissanen et al., (2022) have presented a new type of diffusion process for generative modeling based on heat dissipation, or blurring, as an alternative to isotropic Gaussian diffusion. Here, we show that blurring can equivalently be defined through a Gaussian diffusion process with non-isotropic noise. In making this connection, we bridge the gap between inverse heat dissipation and denoising diffusion, and we shed light on the inductive bias that results from this modeling choice. Finally, we propose a generalized class of diffusion models that offers the best of both standard Gaus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.05557","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2209.05557/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2209.05557","created_at":"2026-07-05T08:13:57.419723+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.05557v3","created_at":"2026-07-05T08:13:57.419723+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.05557","created_at":"2026-07-05T08:13:57.419723+00:00"},{"alias_kind":"pith_short_12","alias_value":"37KLJGTDL455","created_at":"2026-07-05T08:13:57.419723+00:00"},{"alias_kind":"pith_short_16","alias_value":"37KLJGTDL455YSS3","created_at":"2026-07-05T08:13:57.419723+00:00"},{"alias_kind":"pith_short_8","alias_value":"37KLJGTD","created_at":"2026-07-05T08:13:57.419723+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27696","citing_title":"Class-frequency Guided Noise Schedule for Diffusion Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2312.03798","citing_title":"Single Image Reflection Removal with Patch Reflectance Prior","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2506.16827","citing_title":"Beyond Blur: A Fluid Perspective on Generative Diffusion Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08976","citing_title":"Score-Based Generative Modeling through Anisotropic Stochastic Partial Differential Equations","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/37KLJGTDL455YSS3VLL3WBKIAK","json":"https://pith.science/pith/37KLJGTDL455YSS3VLL3WBKIAK.json","graph_json":"https://pith.science/api/pith-number/37KLJGTDL455YSS3VLL3WBKIAK/graph.json","events_json":"https://pith.science/api/pith-number/37KLJGTDL455YSS3VLL3WBKIAK/events.json","paper":"https://pith.science/paper/37KLJGTD"},"agent_actions":{"view_html":"https://pith.science/pith/37KLJGTDL455YSS3VLL3WBKIAK","download_json":"https://pith.science/pith/37KLJGTDL455YSS3VLL3WBKIAK.json","view_paper":"https://pith.science/paper/37KLJGTD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.05557&json=true","fetch_graph":"https://pith.science/api/pith-number/37KLJGTDL455YSS3VLL3WBKIAK/graph.json","fetch_events":"https://pith.science/api/pith-number/37KLJGTDL455YSS3VLL3WBKIAK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37KLJGTDL455YSS3VLL3WBKIAK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37KLJGTDL455YSS3VLL3WBKIAK/action/storage_attestation","attest_author":"https://pith.science/pith/37KLJGTDL455YSS3VLL3WBKIAK/action/author_attestation","sign_citation":"https://pith.science/pith/37KLJGTDL455YSS3VLL3WBKIAK/action/citation_signature","submit_replication":"https://pith.science/pith/37KLJGTDL455YSS3VLL3WBKIAK/action/replication_record"}},"created_at":"2026-07-05T08:13:57.419723+00:00","updated_at":"2026-07-05T08:13:57.419723+00:00"}