{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZRFBHAFFVT6MOELC4ACDFRW5FI","short_pith_number":"pith:ZRFBHAFF","schema_version":"1.0","canonical_sha256":"cc4a1380a5acfcc71162e00432c6dd2a2bc2055c3d6a49a296d645af0a51b82c","source":{"kind":"arxiv","id":"2502.04849","version":1},"attestation_state":"computed","paper":{"title":"Advancing Wasserstein Convergence Analysis of Score-Based Models: Insights from Discretization and Second-Order Acceleration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR"],"primary_cat":"stat.ML","authors_text":"Lu Yu, Yifeng Yu","submitted_at":"2025-02-07T11:37:51Z","abstract_excerpt":"Score-based diffusion models have emerged as powerful tools in generative modeling, yet their theoretical foundations remain underexplored. In this work, we focus on the Wasserstein convergence analysis of score-based diffusion models. Specifically, we investigate the impact of various discretization schemes, including Euler discretization, exponential integrators, and midpoint randomization methods. Our analysis provides a quantitative comparison of these discrete approximations, emphasizing their influence on convergence behavior. Furthermore, we explore scenarios where Hessian information i"},"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":"2502.04849","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-02-07T11:37:51Z","cross_cats_sorted":["cs.LG","math.PR"],"title_canon_sha256":"355854ff6480fb6b26ea7c6e4296d6f39788d56cacd18e34eb4587b8d9b0856f","abstract_canon_sha256":"9bad5ae0f9c81476c19878f78ef3c2f72e4ad899b0c7723fee9532c588b07a66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:58.244379Z","signature_b64":"Na8+g+zCJMUtq6W5+1XSLAmiNc7P5EoCUALqZeiLm5IXmGOixBnega3S0vgGGw1FocJD6/Y79Vw5ukbHuw/6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc4a1380a5acfcc71162e00432c6dd2a2bc2055c3d6a49a296d645af0a51b82c","last_reissued_at":"2026-07-05T10:10:58.243774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:58.243774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advancing Wasserstein Convergence Analysis of Score-Based Models: Insights from Discretization and Second-Order Acceleration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR"],"primary_cat":"stat.ML","authors_text":"Lu Yu, Yifeng Yu","submitted_at":"2025-02-07T11:37:51Z","abstract_excerpt":"Score-based diffusion models have emerged as powerful tools in generative modeling, yet their theoretical foundations remain underexplored. In this work, we focus on the Wasserstein convergence analysis of score-based diffusion models. Specifically, we investigate the impact of various discretization schemes, including Euler discretization, exponential integrators, and midpoint randomization methods. Our analysis provides a quantitative comparison of these discrete approximations, emphasizing their influence on convergence behavior. Furthermore, we explore scenarios where Hessian information i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04849","kind":"arxiv","version":1},"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/2502.04849/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":"2502.04849","created_at":"2026-07-05T10:10:58.243853+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.04849v1","created_at":"2026-07-05T10:10:58.243853+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04849","created_at":"2026-07-05T10:10:58.243853+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZRFBHAFFVT6M","created_at":"2026-07-05T10:10:58.243853+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZRFBHAFFVT6MOELC","created_at":"2026-07-05T10:10:58.243853+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZRFBHAFF","created_at":"2026-07-05T10:10:58.243853+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":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06172","citing_title":"Expressivity of Bi-Lipschitz Normalizing Flows: A Score-Based Diffusion Perspective","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZRFBHAFFVT6MOELC4ACDFRW5FI","json":"https://pith.science/pith/ZRFBHAFFVT6MOELC4ACDFRW5FI.json","graph_json":"https://pith.science/api/pith-number/ZRFBHAFFVT6MOELC4ACDFRW5FI/graph.json","events_json":"https://pith.science/api/pith-number/ZRFBHAFFVT6MOELC4ACDFRW5FI/events.json","paper":"https://pith.science/paper/ZRFBHAFF"},"agent_actions":{"view_html":"https://pith.science/pith/ZRFBHAFFVT6MOELC4ACDFRW5FI","download_json":"https://pith.science/pith/ZRFBHAFFVT6MOELC4ACDFRW5FI.json","view_paper":"https://pith.science/paper/ZRFBHAFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.04849&json=true","fetch_graph":"https://pith.science/api/pith-number/ZRFBHAFFVT6MOELC4ACDFRW5FI/graph.json","fetch_events":"https://pith.science/api/pith-number/ZRFBHAFFVT6MOELC4ACDFRW5FI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZRFBHAFFVT6MOELC4ACDFRW5FI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZRFBHAFFVT6MOELC4ACDFRW5FI/action/storage_attestation","attest_author":"https://pith.science/pith/ZRFBHAFFVT6MOELC4ACDFRW5FI/action/author_attestation","sign_citation":"https://pith.science/pith/ZRFBHAFFVT6MOELC4ACDFRW5FI/action/citation_signature","submit_replication":"https://pith.science/pith/ZRFBHAFFVT6MOELC4ACDFRW5FI/action/replication_record"}},"created_at":"2026-07-05T10:10:58.243853+00:00","updated_at":"2026-07-05T10:10:58.243853+00:00"}