{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZJ2WUW5ZOV7J76INSPY3MABITQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"af9958111ad70e54239e759837b430fb23c28e8bb19800cab48a786658fec8b7","cross_cats_sorted":["math.OC","math.PR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T18:40:45Z","title_canon_sha256":"e6549bbc1423900b566b047d5a14f24c3a1165dbcfa3cd61be51ce8d3ef60058"},"schema_version":"1.0","source":{"id":"2311.13584","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.13584","created_at":"2026-07-05T10:14:37Z"},{"alias_kind":"arxiv_version","alias_value":"2311.13584v5","created_at":"2026-07-05T10:14:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13584","created_at":"2026-07-05T10:14:37Z"},{"alias_kind":"pith_short_12","alias_value":"ZJ2WUW5ZOV7J","created_at":"2026-07-05T10:14:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZJ2WUW5ZOV7J76IN","created_at":"2026-07-05T10:14:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZJ2WUW5Z","created_at":"2026-07-05T10:14:37Z"}],"graph_snapshots":[{"event_id":"sha256:29420cc25c9a1f870600d40a1f94aa071c1be7c38411e9d31c3f53ac6b7c5ba9","target":"graph","created_at":"2026-07-05T10:14:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.13584/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dong-Young Lim, \\\"Omer Deniz Akyildiz, Sotirios Sabanis, Stefano Bruno, Ying Zhang","cross_cats":["math.OC","math.PR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T18:40:45Z","title":"On diffusion-based generative models and their error bounds: The log-concave case with full convergence estimates"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13584","kind":"arxiv","version":5},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6894eb4962f2cc6ea50ccc714a04147684cea0c131c957a0431e7f077ae2f2ba","target":"record","created_at":"2026-07-05T10:14:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"af9958111ad70e54239e759837b430fb23c28e8bb19800cab48a786658fec8b7","cross_cats_sorted":["math.OC","math.PR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T18:40:45Z","title_canon_sha256":"e6549bbc1423900b566b047d5a14f24c3a1165dbcfa3cd61be51ce8d3ef60058"},"schema_version":"1.0","source":{"id":"2311.13584","kind":"arxiv","version":5}},"canonical_sha256":"ca756a5bb9757e9ff90d93f1b600289c299c58060db54a7eb47dd380df2d9385","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca756a5bb9757e9ff90d93f1b600289c299c58060db54a7eb47dd380df2d9385","first_computed_at":"2026-07-05T10:14:37.270474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:37.270474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c9bWewgxiLxDAsCvV7uTczpkhfGA2jM5rWqUIGr2Hh35sf1qbpB1Rc1KavHxHmr0Zrmq7J0YA5rP5H8IuNrSAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:37.270967Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.13584","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6894eb4962f2cc6ea50ccc714a04147684cea0c131c957a0431e7f077ae2f2ba","sha256:29420cc25c9a1f870600d40a1f94aa071c1be7c38411e9d31c3f53ac6b7c5ba9"],"state_sha256":"227ef9dc5acb2536c304a45263d51d59c45573f1a167f687cd61885eaad27776"}