{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JT53BLV6M7XCPKBPP322WPGNLZ","short_pith_number":"pith:JT53BLV6","schema_version":"1.0","canonical_sha256":"4cfbb0aebe67ee27a82f7ef5ab3ccd5e721c7573581e7ac2c66066134df41fa0","source":{"kind":"arxiv","id":"2401.17958","version":2},"attestation_state":"computed","paper":{"title":"Convergence Analysis for General Probability Flow ODEs of Diffusion Models in Wasserstein Distances","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR"],"primary_cat":"stat.ML","authors_text":"Lingjiong Zhu, Xuefeng Gao","submitted_at":"2024-01-31T16:07:44Z","abstract_excerpt":"Score-based generative modeling with probability flow ordinary differential equations (ODEs) has achieved remarkable success in a variety of applications. While various fast ODE-based samplers have been proposed in the literature and employed in practice, the theoretical understandings about convergence properties of the probability flow ODE are still quite limited. In this paper, we provide the first non-asymptotic convergence analysis for a general class of probability flow ODE samplers in 2-Wasserstein distance, assuming accurate score estimates and smooth log-concave data distributions. We"},"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":"2401.17958","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-01-31T16:07:44Z","cross_cats_sorted":["cs.LG","math.PR"],"title_canon_sha256":"c552a24b016674a43967ad4a02d3db808a5d52c1e0193049f29979d5d87e028e","abstract_canon_sha256":"c010b280cef8967a2bc9255f577fd0123e3969bd0750434426b7c0462e11ce9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:14.711256Z","signature_b64":"4vCtwNXFdNa4vYbMA+ZyLJ2ffaCnPH7LiWV2hbxaEmexT8V4AoB7eNyvrDzgG7+WcX/GpGzt/SyBAweZSK1OBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cfbb0aebe67ee27a82f7ef5ab3ccd5e721c7573581e7ac2c66066134df41fa0","last_reissued_at":"2026-07-05T11:51:14.710779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:14.710779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence Analysis for General Probability Flow ODEs of Diffusion Models in Wasserstein Distances","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR"],"primary_cat":"stat.ML","authors_text":"Lingjiong Zhu, Xuefeng Gao","submitted_at":"2024-01-31T16:07:44Z","abstract_excerpt":"Score-based generative modeling with probability flow ordinary differential equations (ODEs) has achieved remarkable success in a variety of applications. While various fast ODE-based samplers have been proposed in the literature and employed in practice, the theoretical understandings about convergence properties of the probability flow ODE are still quite limited. In this paper, we provide the first non-asymptotic convergence analysis for a general class of probability flow ODE samplers in 2-Wasserstein distance, assuming accurate score estimates and smooth log-concave data distributions. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17958","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/2401.17958/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":"2401.17958","created_at":"2026-07-05T11:51:14.710829+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.17958v2","created_at":"2026-07-05T11:51:14.710829+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17958","created_at":"2026-07-05T11:51:14.710829+00:00"},{"alias_kind":"pith_short_12","alias_value":"JT53BLV6M7XC","created_at":"2026-07-05T11:51:14.710829+00:00"},{"alias_kind":"pith_short_16","alias_value":"JT53BLV6M7XCPKBP","created_at":"2026-07-05T11:51:14.710829+00:00"},{"alias_kind":"pith_short_8","alias_value":"JT53BLV6","created_at":"2026-07-05T11:51:14.710829+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06646","citing_title":"Diffusion enabled Optimal Transport distances for graph matching","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23920","citing_title":"Catastrophic Compositional Generation: Why Vanilla Diffusion Models Fail to Extrapolate","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03360","citing_title":"Structured drift design for denoising diffusion models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27769","citing_title":"Smoothed Score Queries and the Complexity of Sampling","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21911","citing_title":"Noise Schedule Design for Diffusion Models: An Optimal Control Perspective","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10857","citing_title":"Query Lower Bounds for Diffusion Sampling","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06065","citing_title":"Lipschitz regularity in Flow Matching and Diffusion Models: sharp sampling rates and functional inequalities","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JT53BLV6M7XCPKBPP322WPGNLZ","json":"https://pith.science/pith/JT53BLV6M7XCPKBPP322WPGNLZ.json","graph_json":"https://pith.science/api/pith-number/JT53BLV6M7XCPKBPP322WPGNLZ/graph.json","events_json":"https://pith.science/api/pith-number/JT53BLV6M7XCPKBPP322WPGNLZ/events.json","paper":"https://pith.science/paper/JT53BLV6"},"agent_actions":{"view_html":"https://pith.science/pith/JT53BLV6M7XCPKBPP322WPGNLZ","download_json":"https://pith.science/pith/JT53BLV6M7XCPKBPP322WPGNLZ.json","view_paper":"https://pith.science/paper/JT53BLV6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.17958&json=true","fetch_graph":"https://pith.science/api/pith-number/JT53BLV6M7XCPKBPP322WPGNLZ/graph.json","fetch_events":"https://pith.science/api/pith-number/JT53BLV6M7XCPKBPP322WPGNLZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JT53BLV6M7XCPKBPP322WPGNLZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JT53BLV6M7XCPKBPP322WPGNLZ/action/storage_attestation","attest_author":"https://pith.science/pith/JT53BLV6M7XCPKBPP322WPGNLZ/action/author_attestation","sign_citation":"https://pith.science/pith/JT53BLV6M7XCPKBPP322WPGNLZ/action/citation_signature","submit_replication":"https://pith.science/pith/JT53BLV6M7XCPKBPP322WPGNLZ/action/replication_record"}},"created_at":"2026-07-05T11:51:14.710829+00:00","updated_at":"2026-07-05T11:51:14.710829+00:00"}