{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V44B4HFU2LP47EX2237S65J4FX","short_pith_number":"pith:V44B4HFU","schema_version":"1.0","canonical_sha256":"af381e1cb4d2dfcf92fad6ff2f753c2dff97690bdb9be4dddff0a7563804e94e","source":{"kind":"arxiv","id":"2506.19559","version":1},"attestation_state":"computed","paper":{"title":"Regularity of the score function in generative models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Arthur St\\'ephanovitch","submitted_at":"2025-06-24T12:16:06Z","abstract_excerpt":"We study the regularity of the score function in score-based generative models and show that it naturally adapts to the smoothness of the data distribution. Under minimal assumptions, we establish Lipschitz estimates that directly support convergence and stability analyses in both diffusion and ODE-based generative models. In addition, we derive higher-order regularity bounds, which simplify existing arguments for optimally approximating the score function using neural networks."},"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":"2506.19559","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2025-06-24T12:16:06Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"e08b0d571c58f2455e38bf2334d52a5a052f4cf29143809a909ef79bc6696068","abstract_canon_sha256":"2817652625ab05b6f492e261c95673559252809e222276790245facd0f643106"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:34.524875Z","signature_b64":"TO821ktbMzPIryvTJwgj6KF/25SpRVcQJUp9BQu8FAS+m7nafpxfgUvnNrtOiAR6QhZbsVPOx8KG7AjXwEXIBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af381e1cb4d2dfcf92fad6ff2f753c2dff97690bdb9be4dddff0a7563804e94e","last_reissued_at":"2026-07-05T11:26:34.524386Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:34.524386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regularity of the score function in generative models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Arthur St\\'ephanovitch","submitted_at":"2025-06-24T12:16:06Z","abstract_excerpt":"We study the regularity of the score function in score-based generative models and show that it naturally adapts to the smoothness of the data distribution. Under minimal assumptions, we establish Lipschitz estimates that directly support convergence and stability analyses in both diffusion and ODE-based generative models. In addition, we derive higher-order regularity bounds, which simplify existing arguments for optimally approximating the score function using neural networks."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19559","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/2506.19559/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":"2506.19559","created_at":"2026-07-05T11:26:34.524450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19559v1","created_at":"2026-07-05T11:26:34.524450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19559","created_at":"2026-07-05T11:26:34.524450+00:00"},{"alias_kind":"pith_short_12","alias_value":"V44B4HFU2LP4","created_at":"2026-07-05T11:26:34.524450+00:00"},{"alias_kind":"pith_short_16","alias_value":"V44B4HFU2LP47EX2","created_at":"2026-07-05T11:26:34.524450+00:00"},{"alias_kind":"pith_short_8","alias_value":"V44B4HFU","created_at":"2026-07-05T11:26:34.524450+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18069","citing_title":"Wasserstein bounds for denoising diffusion probabilistic models via the F\\\"ollmer process","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06172","citing_title":"Expressivity of Bi-Lipschitz Normalizing Flows: A Score-Based Diffusion Perspective","ref_index":45,"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":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V44B4HFU2LP47EX2237S65J4FX","json":"https://pith.science/pith/V44B4HFU2LP47EX2237S65J4FX.json","graph_json":"https://pith.science/api/pith-number/V44B4HFU2LP47EX2237S65J4FX/graph.json","events_json":"https://pith.science/api/pith-number/V44B4HFU2LP47EX2237S65J4FX/events.json","paper":"https://pith.science/paper/V44B4HFU"},"agent_actions":{"view_html":"https://pith.science/pith/V44B4HFU2LP47EX2237S65J4FX","download_json":"https://pith.science/pith/V44B4HFU2LP47EX2237S65J4FX.json","view_paper":"https://pith.science/paper/V44B4HFU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19559&json=true","fetch_graph":"https://pith.science/api/pith-number/V44B4HFU2LP47EX2237S65J4FX/graph.json","fetch_events":"https://pith.science/api/pith-number/V44B4HFU2LP47EX2237S65J4FX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V44B4HFU2LP47EX2237S65J4FX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V44B4HFU2LP47EX2237S65J4FX/action/storage_attestation","attest_author":"https://pith.science/pith/V44B4HFU2LP47EX2237S65J4FX/action/author_attestation","sign_citation":"https://pith.science/pith/V44B4HFU2LP47EX2237S65J4FX/action/citation_signature","submit_replication":"https://pith.science/pith/V44B4HFU2LP47EX2237S65J4FX/action/replication_record"}},"created_at":"2026-07-05T11:26:34.524450+00:00","updated_at":"2026-07-05T11:26:34.524450+00:00"}