{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZJ2WUW5ZOV7J76INSPY3MABITQ","short_pith_number":"pith:ZJ2WUW5Z","schema_version":"1.0","canonical_sha256":"ca756a5bb9757e9ff90d93f1b600289c299c58060db54a7eb47dd380df2d9385","source":{"kind":"arxiv","id":"2311.13584","version":5},"attestation_state":"computed","paper":{"title":"On diffusion-based generative models and their error bounds: The log-concave case with full convergence estimates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","math.PR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dong-Young Lim, \\\"Omer Deniz Akyildiz, Sotirios Sabanis, Stefano Bruno, Ying Zhang","submitted_at":"2023-11-22T18:40:45Z","abstract_excerpt":"We provide full theoretical guarantees for the convergence behaviour of diffusion-based generative models under the assumption of strongly log-concave data distributions while our approximating class of functions used for score estimation is made of Lipschitz continuous functions avoiding any Lipschitzness assumption on the score function. We demonstrate via a motivating example, sampling from a Gaussian distribution with unknown mean, the powerfulness of our approach. In this case, explicit estimates are provided for the associated optimization problem, i.e. score approximation, while these a"},"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":"2311.13584","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T18:40:45Z","cross_cats_sorted":["math.OC","math.PR","stat.ML"],"title_canon_sha256":"e6549bbc1423900b566b047d5a14f24c3a1165dbcfa3cd61be51ce8d3ef60058","abstract_canon_sha256":"af9958111ad70e54239e759837b430fb23c28e8bb19800cab48a786658fec8b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:37.270967Z","signature_b64":"c9bWewgxiLxDAsCvV7uTczpkhfGA2jM5rWqUIGr2Hh35sf1qbpB1Rc1KavHxHmr0Zrmq7J0YA5rP5H8IuNrSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca756a5bb9757e9ff90d93f1b600289c299c58060db54a7eb47dd380df2d9385","last_reissued_at":"2026-07-05T10:14:37.270474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:37.270474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On diffusion-based generative models and their error bounds: The log-concave case with full convergence estimates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","math.PR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dong-Young Lim, \\\"Omer Deniz Akyildiz, Sotirios Sabanis, Stefano Bruno, Ying Zhang","submitted_at":"2023-11-22T18:40:45Z","abstract_excerpt":"We provide full theoretical guarantees for the convergence behaviour of diffusion-based generative models under the assumption of strongly log-concave data distributions while our approximating class of functions used for score estimation is made of Lipschitz continuous functions avoiding any Lipschitzness assumption on the score function. We demonstrate via a motivating example, sampling from a Gaussian distribution with unknown mean, the powerfulness of our approach. In this case, explicit estimates are provided for the associated optimization problem, i.e. score approximation, while these a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13584","kind":"arxiv","version":5},"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/2311.13584/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":"2311.13584","created_at":"2026-07-05T10:14:37.270528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.13584v5","created_at":"2026-07-05T10:14:37.270528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13584","created_at":"2026-07-05T10:14:37.270528+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJ2WUW5ZOV7J","created_at":"2026-07-05T10:14:37.270528+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJ2WUW5ZOV7J76IN","created_at":"2026-07-05T10:14:37.270528+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJ2WUW5Z","created_at":"2026-07-05T10:14:37.270528+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28134","citing_title":"Convergence of empirical subgradients for optimal transport-based objectives","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15822","citing_title":"Intrinsic Wasserstein Rates for Score-Based Generative Models on Smooth Manifolds","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07513","citing_title":"Tessellations of Semi-Discrete Flow Matching","ref_index":296,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJ2WUW5ZOV7J76INSPY3MABITQ","json":"https://pith.science/pith/ZJ2WUW5ZOV7J76INSPY3MABITQ.json","graph_json":"https://pith.science/api/pith-number/ZJ2WUW5ZOV7J76INSPY3MABITQ/graph.json","events_json":"https://pith.science/api/pith-number/ZJ2WUW5ZOV7J76INSPY3MABITQ/events.json","paper":"https://pith.science/paper/ZJ2WUW5Z"},"agent_actions":{"view_html":"https://pith.science/pith/ZJ2WUW5ZOV7J76INSPY3MABITQ","download_json":"https://pith.science/pith/ZJ2WUW5ZOV7J76INSPY3MABITQ.json","view_paper":"https://pith.science/paper/ZJ2WUW5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.13584&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJ2WUW5ZOV7J76INSPY3MABITQ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJ2WUW5ZOV7J76INSPY3MABITQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJ2WUW5ZOV7J76INSPY3MABITQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJ2WUW5ZOV7J76INSPY3MABITQ/action/storage_attestation","attest_author":"https://pith.science/pith/ZJ2WUW5ZOV7J76INSPY3MABITQ/action/author_attestation","sign_citation":"https://pith.science/pith/ZJ2WUW5ZOV7J76INSPY3MABITQ/action/citation_signature","submit_replication":"https://pith.science/pith/ZJ2WUW5ZOV7J76INSPY3MABITQ/action/replication_record"}},"created_at":"2026-07-05T10:14:37.270528+00:00","updated_at":"2026-07-05T10:14:37.270528+00:00"}