{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OYU7WL7JKYRB4ENLF5SFI7PPOK","short_pith_number":"pith:OYU7WL7J","schema_version":"1.0","canonical_sha256":"7629fb2fe956221e11ab2f64547def72be9ee84613b9c06e8181d27359cd04dd","source":{"kind":"arxiv","id":"2405.16418","version":2},"attestation_state":"computed","paper":{"title":"Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Yingyu Liang, Yufa Zhou, Zhao Song, Zhenmei Shi","submitted_at":"2024-05-26T03:32:27Z","abstract_excerpt":"Diffusion models have made rapid progress in generating high-quality samples across various domains. However, a theoretical understanding of the Lipschitz continuity and second momentum properties of the diffusion process is still lacking. In this paper, we bridge this gap by providing a detailed examination of these smoothness properties for the case where the target data distribution is a mixture of Gaussians, which serves as a universal approximator for smooth densities such as image data. We prove that if the target distribution is a $k$-mixture of Gaussians, the density of the entire diff"},"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":"2405.16418","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-26T03:32:27Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"6640f7d17182fd791ab7d59a7ae82d6d9f558f7b74768bb28d0d41e7afd70dcd","abstract_canon_sha256":"aa4c0cc3b27290bbd45b109039aed57062dd718caf301869db5d2ab94546883d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:57.788012Z","signature_b64":"393C1yTmf1pEDk9JVF1ZTJltQ5iibsZc4tobE4ORS5Mt6mRqnGAci9zwW92RwHrU67pvg1+WUVnTwIRE+xEKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7629fb2fe956221e11ab2f64547def72be9ee84613b9c06e8181d27359cd04dd","last_reissued_at":"2026-07-05T09:19:57.787566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:57.787566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Yingyu Liang, Yufa Zhou, Zhao Song, Zhenmei Shi","submitted_at":"2024-05-26T03:32:27Z","abstract_excerpt":"Diffusion models have made rapid progress in generating high-quality samples across various domains. However, a theoretical understanding of the Lipschitz continuity and second momentum properties of the diffusion process is still lacking. In this paper, we bridge this gap by providing a detailed examination of these smoothness properties for the case where the target data distribution is a mixture of Gaussians, which serves as a universal approximator for smooth densities such as image data. We prove that if the target distribution is a $k$-mixture of Gaussians, the density of the entire diff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16418","kind":"arxiv","version":2},"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/2405.16418/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":"2405.16418","created_at":"2026-07-05T09:19:57.787623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16418v2","created_at":"2026-07-05T09:19:57.787623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16418","created_at":"2026-07-05T09:19:57.787623+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYU7WL7JKYRB","created_at":"2026-07-05T09:19:57.787623+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYU7WL7JKYRB4ENL","created_at":"2026-07-05T09:19:57.787623+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYU7WL7J","created_at":"2026-07-05T09:19:57.787623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06065","citing_title":"Lipschitz regularity in Flow Matching and Diffusion Models: sharp sampling rates and functional inequalities","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OYU7WL7JKYRB4ENLF5SFI7PPOK","json":"https://pith.science/pith/OYU7WL7JKYRB4ENLF5SFI7PPOK.json","graph_json":"https://pith.science/api/pith-number/OYU7WL7JKYRB4ENLF5SFI7PPOK/graph.json","events_json":"https://pith.science/api/pith-number/OYU7WL7JKYRB4ENLF5SFI7PPOK/events.json","paper":"https://pith.science/paper/OYU7WL7J"},"agent_actions":{"view_html":"https://pith.science/pith/OYU7WL7JKYRB4ENLF5SFI7PPOK","download_json":"https://pith.science/pith/OYU7WL7JKYRB4ENLF5SFI7PPOK.json","view_paper":"https://pith.science/paper/OYU7WL7J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16418&json=true","fetch_graph":"https://pith.science/api/pith-number/OYU7WL7JKYRB4ENLF5SFI7PPOK/graph.json","fetch_events":"https://pith.science/api/pith-number/OYU7WL7JKYRB4ENLF5SFI7PPOK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYU7WL7JKYRB4ENLF5SFI7PPOK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYU7WL7JKYRB4ENLF5SFI7PPOK/action/storage_attestation","attest_author":"https://pith.science/pith/OYU7WL7JKYRB4ENLF5SFI7PPOK/action/author_attestation","sign_citation":"https://pith.science/pith/OYU7WL7JKYRB4ENLF5SFI7PPOK/action/citation_signature","submit_replication":"https://pith.science/pith/OYU7WL7JKYRB4ENLF5SFI7PPOK/action/replication_record"}},"created_at":"2026-07-05T09:19:57.787623+00:00","updated_at":"2026-07-05T09:19:57.787623+00:00"}