{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HXVJ5RGABYBJPLHYLRYLFBU3II","short_pith_number":"pith:HXVJ5RGA","schema_version":"1.0","canonical_sha256":"3dea9ec4c00e0297acf85c70b2869b42383f69624d85b6e1c6385f36ae35d1f2","source":{"kind":"arxiv","id":"2409.18804","version":2},"attestation_state":"computed","paper":{"title":"Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions","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, Judith Rousseau","submitted_at":"2024-09-27T14:57:18Z","abstract_excerpt":"Denoising Diffusion Probabilistic Models (DDPM) are powerful state-of-the-art methods used to generate synthetic data from high-dimensional data distributions and are widely used for image, audio, and video generation as well as many more applications in science and beyond. The \\textit{manifold hypothesis} states that high-dimensional data often lie on lower-dimensional manifolds within the ambient space, and is widely believed to hold in provided examples. While recent results have provided invaluable insight into how diffusion models adapt to the manifold hypothesis, they do not capture the "},"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":"2409.18804","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-09-27T14:57:18Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"10bcbfd4d0ffe773cb6d7d1673c93355db841bbf34289e786f4ea2a6ed6d21ec","abstract_canon_sha256":"1a21faeb3be4227f8347de7244f83f719ec2db6067043a8b45e2e4732570f3eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:11.884714Z","signature_b64":"T+2b9HdOlIPDJLoiewVGQTUFNCUrUFNEd9toJpF//DacE4NJHhHjBWTQAdaFxrnlmIW0WMHaBMjyhrIyhpLGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3dea9ec4c00e0297acf85c70b2869b42383f69624d85b6e1c6385f36ae35d1f2","last_reissued_at":"2026-07-05T10:53:11.884216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:11.884216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions","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, Judith Rousseau","submitted_at":"2024-09-27T14:57:18Z","abstract_excerpt":"Denoising Diffusion Probabilistic Models (DDPM) are powerful state-of-the-art methods used to generate synthetic data from high-dimensional data distributions and are widely used for image, audio, and video generation as well as many more applications in science and beyond. The \\textit{manifold hypothesis} states that high-dimensional data often lie on lower-dimensional manifolds within the ambient space, and is widely believed to hold in provided examples. While recent results have provided invaluable insight into how diffusion models adapt to the manifold hypothesis, they do not capture the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18804","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/2409.18804/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":"2409.18804","created_at":"2026-07-05T10:53:11.884282+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.18804v2","created_at":"2026-07-05T10:53:11.884282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18804","created_at":"2026-07-05T10:53:11.884282+00:00"},{"alias_kind":"pith_short_12","alias_value":"HXVJ5RGABYBJ","created_at":"2026-07-05T10:53:11.884282+00:00"},{"alias_kind":"pith_short_16","alias_value":"HXVJ5RGABYBJPLHY","created_at":"2026-07-05T10:53:11.884282+00:00"},{"alias_kind":"pith_short_8","alias_value":"HXVJ5RGA","created_at":"2026-07-05T10:53:11.884282+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"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":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19084","citing_title":"Optimal score function estimation via derivatives constraints","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00094","citing_title":"Diffusion Image Generation with Explicit Modeling of Data Manifold Geometry","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04126","citing_title":"Simultaneous CNN Approximation on Manifolds with Applications to Boundary Value Problems","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00094","citing_title":"Diffusion Image Generation with Explicit Modeling of Data Manifold Geometry","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22950","citing_title":"Diffusion-based Denoising Beats Vanilla Score Matching in Parameter Estimation: A Theoretical Explanation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2509.19707","citing_title":"Diffusion and Flow-based Copulas: Forgetting and Remembering Dependencies","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20235","citing_title":"Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15822","citing_title":"Intrinsic Wasserstein Rates for Score-Based Generative Models on Smooth Manifolds","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18040","citing_title":"A note on connections between the F\\\"ollmer process and the denoising diffusion probabilistic model","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2603.20645","citing_title":"Diffusion Model for Manifold Data: Score Decomposition, Curvature, and Statistical Complexity","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14168","citing_title":"Finite Sample Bounds for Learning with Score Matching","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13448","citing_title":"On the Limits of Latent Reuse in Diffusion Models","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06077","citing_title":"Understanding diffusion models requires rethinking (again) generalization","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10074","citing_title":"Transformers Learn the Optimal DDPM Denoiser for Multi-Token GMMs","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07625","citing_title":"Statistical Convergence of Spherical First Hitting Diffusion Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04126","citing_title":"Simultaneous CNN Approximation on Manifolds with Applications to Boundary Value Problems","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HXVJ5RGABYBJPLHYLRYLFBU3II","json":"https://pith.science/pith/HXVJ5RGABYBJPLHYLRYLFBU3II.json","graph_json":"https://pith.science/api/pith-number/HXVJ5RGABYBJPLHYLRYLFBU3II/graph.json","events_json":"https://pith.science/api/pith-number/HXVJ5RGABYBJPLHYLRYLFBU3II/events.json","paper":"https://pith.science/paper/HXVJ5RGA"},"agent_actions":{"view_html":"https://pith.science/pith/HXVJ5RGABYBJPLHYLRYLFBU3II","download_json":"https://pith.science/pith/HXVJ5RGABYBJPLHYLRYLFBU3II.json","view_paper":"https://pith.science/paper/HXVJ5RGA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.18804&json=true","fetch_graph":"https://pith.science/api/pith-number/HXVJ5RGABYBJPLHYLRYLFBU3II/graph.json","fetch_events":"https://pith.science/api/pith-number/HXVJ5RGABYBJPLHYLRYLFBU3II/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HXVJ5RGABYBJPLHYLRYLFBU3II/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HXVJ5RGABYBJPLHYLRYLFBU3II/action/storage_attestation","attest_author":"https://pith.science/pith/HXVJ5RGABYBJPLHYLRYLFBU3II/action/author_attestation","sign_citation":"https://pith.science/pith/HXVJ5RGABYBJPLHYLRYLFBU3II/action/citation_signature","submit_replication":"https://pith.science/pith/HXVJ5RGABYBJPLHYLRYLFBU3II/action/replication_record"}},"created_at":"2026-07-05T10:53:11.884282+00:00","updated_at":"2026-07-05T10:53:11.884282+00:00"}