{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KS2PA7X7CIKYFR7P6GOKGI65EE","short_pith_number":"pith:KS2PA7X7","schema_version":"1.0","canonical_sha256":"54b4f07eff121582c7eff19ca323dd2109f5b2de69d66c0f51861fa86ffa7c3e","source":{"kind":"arxiv","id":"2410.09046","version":2},"attestation_state":"computed","paper":{"title":"Linear Convergence of Diffusion Models Under the Manifold Hypothesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"George Deligiannidis, Iskander Azangulov, Peter Potaptchik","submitted_at":"2024-10-11T17:58:30Z","abstract_excerpt":"Score-matching generative models have proven successful at sampling from complex high-dimensional data distributions. In many applications, this distribution is believed to concentrate on a much lower $d$-dimensional manifold embedded into $D$-dimensional space; this is known as the manifold hypothesis. The current best-known convergence guarantees are either linear in $D$ or polynomial (superlinear) in $d$. The latter exploits a novel integration scheme for the backward SDE. We take the best of both worlds and show that the number of steps diffusion models require in order to converge in Kull"},"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":"2410.09046","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-11T17:58:30Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"473bb9ba44c1b247874417d1099477242517a195bd88e686d115fbb7327e91a1","abstract_canon_sha256":"3df251aa25b9939d1aed205f3abe8c777dc9fa340e6af363f01fdabec493545e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:12.426182Z","signature_b64":"dJtJ4gdSlL2ux8F521zSIfzf2TCSVJLb/966sFf2TNcgBLBrwkKRhtZ81pzXHgRMpPz01C+GVFpEDdmPXjHxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54b4f07eff121582c7eff19ca323dd2109f5b2de69d66c0f51861fa86ffa7c3e","last_reissued_at":"2026-07-05T10:53:12.425700Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:12.425700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Linear Convergence of Diffusion Models Under the Manifold Hypothesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"George Deligiannidis, Iskander Azangulov, Peter Potaptchik","submitted_at":"2024-10-11T17:58:30Z","abstract_excerpt":"Score-matching generative models have proven successful at sampling from complex high-dimensional data distributions. In many applications, this distribution is believed to concentrate on a much lower $d$-dimensional manifold embedded into $D$-dimensional space; this is known as the manifold hypothesis. The current best-known convergence guarantees are either linear in $D$ or polynomial (superlinear) in $d$. The latter exploits a novel integration scheme for the backward SDE. We take the best of both worlds and show that the number of steps diffusion models require in order to converge in Kull"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09046","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/2410.09046/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":"2410.09046","created_at":"2026-07-05T10:53:12.425757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09046v2","created_at":"2026-07-05T10:53:12.425757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09046","created_at":"2026-07-05T10:53:12.425757+00:00"},{"alias_kind":"pith_short_12","alias_value":"KS2PA7X7CIKY","created_at":"2026-07-05T10:53:12.425757+00:00"},{"alias_kind":"pith_short_16","alias_value":"KS2PA7X7CIKYFR7P","created_at":"2026-07-05T10:53:12.425757+00:00"},{"alias_kind":"pith_short_8","alias_value":"KS2PA7X7","created_at":"2026-07-05T10:53:12.425757+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23627","citing_title":"Diffusion Models Adapt to Low-Dimensional Structure Under Flexible Coefficient Choices","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20235","citing_title":"Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KS2PA7X7CIKYFR7P6GOKGI65EE","json":"https://pith.science/pith/KS2PA7X7CIKYFR7P6GOKGI65EE.json","graph_json":"https://pith.science/api/pith-number/KS2PA7X7CIKYFR7P6GOKGI65EE/graph.json","events_json":"https://pith.science/api/pith-number/KS2PA7X7CIKYFR7P6GOKGI65EE/events.json","paper":"https://pith.science/paper/KS2PA7X7"},"agent_actions":{"view_html":"https://pith.science/pith/KS2PA7X7CIKYFR7P6GOKGI65EE","download_json":"https://pith.science/pith/KS2PA7X7CIKYFR7P6GOKGI65EE.json","view_paper":"https://pith.science/paper/KS2PA7X7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09046&json=true","fetch_graph":"https://pith.science/api/pith-number/KS2PA7X7CIKYFR7P6GOKGI65EE/graph.json","fetch_events":"https://pith.science/api/pith-number/KS2PA7X7CIKYFR7P6GOKGI65EE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KS2PA7X7CIKYFR7P6GOKGI65EE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KS2PA7X7CIKYFR7P6GOKGI65EE/action/storage_attestation","attest_author":"https://pith.science/pith/KS2PA7X7CIKYFR7P6GOKGI65EE/action/author_attestation","sign_citation":"https://pith.science/pith/KS2PA7X7CIKYFR7P6GOKGI65EE/action/citation_signature","submit_replication":"https://pith.science/pith/KS2PA7X7CIKYFR7P6GOKGI65EE/action/replication_record"}},"created_at":"2026-07-05T10:53:12.425757+00:00","updated_at":"2026-07-05T10:53:12.425757+00:00"}