{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:U6NFQZZ635Z5DCR3X4IV2OPMDB","short_pith_number":"pith:U6NFQZZ6","schema_version":"1.0","canonical_sha256":"a79a58673edf73d18a3bbf115d39ec187fe76f74a132b7bb418363c5f8b8b10c","source":{"kind":"arxiv","id":"2211.01916","version":2},"attestation_state":"computed","paper":{"title":"Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness Assumptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Holden Lee, Hongrui Chen, Jianfeng Lu","submitted_at":"2022-11-03T15:51:00Z","abstract_excerpt":"We give an improved theoretical analysis of score-based generative modeling. Under a score estimate with small $L^2$ error (averaged across timesteps), we provide efficient convergence guarantees for any data distribution with second-order moment, by either employing early stopping or assuming smoothness condition on the score function of the data distribution. Our result does not rely on any log-concavity or functional inequality assumption and has a logarithmic dependence on the smoothness. In particular, we show that under only a finite second moment condition, approximating the following 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":"2211.01916","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-03T15:51:00Z","cross_cats_sorted":[],"title_canon_sha256":"efa51e26098137b4a82ab1ae120dc6dd8db10fea5f623a1b9fcfca5438a1ceee","abstract_canon_sha256":"9c6a024e54c8d42c33cc0020e76ee8f93aadb4318baf274c03fed7b2a8733ea2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:09.907473Z","signature_b64":"GfCxQjnvZNZ0q1ciME6i1Wxg7YjPLm5rJTe5Pcl7Nu3BbE43cv3taxm59JbA3G8z9vyu+F9nPBTV4dwL8wqwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a79a58673edf73d18a3bbf115d39ec187fe76f74a132b7bb418363c5f8b8b10c","last_reissued_at":"2026-07-05T05:38:09.907093Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:09.907093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness Assumptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Holden Lee, Hongrui Chen, Jianfeng Lu","submitted_at":"2022-11-03T15:51:00Z","abstract_excerpt":"We give an improved theoretical analysis of score-based generative modeling. Under a score estimate with small $L^2$ error (averaged across timesteps), we provide efficient convergence guarantees for any data distribution with second-order moment, by either employing early stopping or assuming smoothness condition on the score function of the data distribution. Our result does not rely on any log-concavity or functional inequality assumption and has a logarithmic dependence on the smoothness. In particular, we show that under only a finite second moment condition, approximating the following i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.01916","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/2211.01916/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":"2211.01916","created_at":"2026-07-05T05:38:09.907143+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.01916v2","created_at":"2026-07-05T05:38:09.907143+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.01916","created_at":"2026-07-05T05:38:09.907143+00:00"},{"alias_kind":"pith_short_12","alias_value":"U6NFQZZ635Z5","created_at":"2026-07-05T05:38:09.907143+00:00"},{"alias_kind":"pith_short_16","alias_value":"U6NFQZZ635Z5DCR3","created_at":"2026-07-05T05:38:09.907143+00:00"},{"alias_kind":"pith_short_8","alias_value":"U6NFQZZ6","created_at":"2026-07-05T05:38:09.907143+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01693","citing_title":"A Mathematical Introduction to Diffusion Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05530","citing_title":"Energy Generative Modeling: A Lyapunov-based Energy Matching Perspective","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U6NFQZZ635Z5DCR3X4IV2OPMDB","json":"https://pith.science/pith/U6NFQZZ635Z5DCR3X4IV2OPMDB.json","graph_json":"https://pith.science/api/pith-number/U6NFQZZ635Z5DCR3X4IV2OPMDB/graph.json","events_json":"https://pith.science/api/pith-number/U6NFQZZ635Z5DCR3X4IV2OPMDB/events.json","paper":"https://pith.science/paper/U6NFQZZ6"},"agent_actions":{"view_html":"https://pith.science/pith/U6NFQZZ635Z5DCR3X4IV2OPMDB","download_json":"https://pith.science/pith/U6NFQZZ635Z5DCR3X4IV2OPMDB.json","view_paper":"https://pith.science/paper/U6NFQZZ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.01916&json=true","fetch_graph":"https://pith.science/api/pith-number/U6NFQZZ635Z5DCR3X4IV2OPMDB/graph.json","fetch_events":"https://pith.science/api/pith-number/U6NFQZZ635Z5DCR3X4IV2OPMDB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U6NFQZZ635Z5DCR3X4IV2OPMDB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U6NFQZZ635Z5DCR3X4IV2OPMDB/action/storage_attestation","attest_author":"https://pith.science/pith/U6NFQZZ635Z5DCR3X4IV2OPMDB/action/author_attestation","sign_citation":"https://pith.science/pith/U6NFQZZ635Z5DCR3X4IV2OPMDB/action/citation_signature","submit_replication":"https://pith.science/pith/U6NFQZZ635Z5DCR3X4IV2OPMDB/action/replication_record"}},"created_at":"2026-07-05T05:38:09.907143+00:00","updated_at":"2026-07-05T05:38:09.907143+00:00"}