{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PYT7RCDGJLCASJJ2MUGMV3B5JP","short_pith_number":"pith:PYT7RCDG","schema_version":"1.0","canonical_sha256":"7e27f888664ac409253a650ccaec3d4bc0766521bf7357c64426b662599cf4f7","source":{"kind":"arxiv","id":"2507.04794","version":1},"attestation_state":"computed","paper":{"title":"Generalization bounds for score-based generative models: a synthetic proof","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Arthur St\\'ephanovitch, Cl\\'ement Levrard, Eddie Aamari","submitted_at":"2025-07-07T09:13:09Z","abstract_excerpt":"We establish minimax convergence rates for score-based generative models (SGMs) under the $1$-Wasserstein distance. Assuming the target density $p^\\star$ lies in a nonparametric $\\beta$-smooth H\\\"older class with either compact support or subGaussian tails on $\\mathbb{R}^d$, we prove that neural network-based score estimators trained via denoising score matching yield generative models achieving rate $n^{-(\\beta+1)/(2\\beta+d)}$ up to polylogarithmic factors. Our unified analysis handles arbitrary smoothness $\\beta > 0$, supports both deterministic and stochastic samplers, and leverages shape c"},"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":"2507.04794","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2025-07-07T09:13:09Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"3ad26fa14f7ae071cd610cebae2912ca31bd1cfa3003325672373a6e34dbb741","abstract_canon_sha256":"6f73ebef98a6ddc5fa4560bcf0cf1a07944de31cdf48c2706f9ab73305eebc8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:54.294031Z","signature_b64":"itzPDg3FhlwCYxmfZKHh7O/GBTujBj+bRf+I5cQXCpsJXeFSn5AIqhS95gB52ljaIvamiCovFucZzmg9DYH0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e27f888664ac409253a650ccaec3d4bc0766521bf7357c64426b662599cf4f7","last_reissued_at":"2026-07-05T11:32:54.293520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:54.293520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalization bounds for score-based generative models: a synthetic proof","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Arthur St\\'ephanovitch, Cl\\'ement Levrard, Eddie Aamari","submitted_at":"2025-07-07T09:13:09Z","abstract_excerpt":"We establish minimax convergence rates for score-based generative models (SGMs) under the $1$-Wasserstein distance. Assuming the target density $p^\\star$ lies in a nonparametric $\\beta$-smooth H\\\"older class with either compact support or subGaussian tails on $\\mathbb{R}^d$, we prove that neural network-based score estimators trained via denoising score matching yield generative models achieving rate $n^{-(\\beta+1)/(2\\beta+d)}$ up to polylogarithmic factors. Our unified analysis handles arbitrary smoothness $\\beta > 0$, supports both deterministic and stochastic samplers, and leverages shape c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04794","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/2507.04794/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":"2507.04794","created_at":"2026-07-05T11:32:54.293583+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04794v1","created_at":"2026-07-05T11:32:54.293583+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04794","created_at":"2026-07-05T11:32:54.293583+00:00"},{"alias_kind":"pith_short_12","alias_value":"PYT7RCDGJLCA","created_at":"2026-07-05T11:32:54.293583+00:00"},{"alias_kind":"pith_short_16","alias_value":"PYT7RCDGJLCASJJ2","created_at":"2026-07-05T11:32:54.293583+00:00"},{"alias_kind":"pith_short_8","alias_value":"PYT7RCDG","created_at":"2026-07-05T11:32:54.293583+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13175","citing_title":"Do Heavy Tails Help Diffusion? On the Subtle Trade-off Between Initialization and Training","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15822","citing_title":"Intrinsic Wasserstein Rates for Score-Based Generative Models on Smooth Manifolds","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13175","citing_title":"Do Heavy Tails Help Diffusion? On the Subtle Trade-off Between Initialization and Training","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22712","citing_title":"Statistical Analysis of Markovian Generative Modeling","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06077","citing_title":"Understanding diffusion models requires rethinking (again) generalization","ref_index":54,"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":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07625","citing_title":"Statistical Convergence of Spherical First Hitting Diffusion Models","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PYT7RCDGJLCASJJ2MUGMV3B5JP","json":"https://pith.science/pith/PYT7RCDGJLCASJJ2MUGMV3B5JP.json","graph_json":"https://pith.science/api/pith-number/PYT7RCDGJLCASJJ2MUGMV3B5JP/graph.json","events_json":"https://pith.science/api/pith-number/PYT7RCDGJLCASJJ2MUGMV3B5JP/events.json","paper":"https://pith.science/paper/PYT7RCDG"},"agent_actions":{"view_html":"https://pith.science/pith/PYT7RCDGJLCASJJ2MUGMV3B5JP","download_json":"https://pith.science/pith/PYT7RCDGJLCASJJ2MUGMV3B5JP.json","view_paper":"https://pith.science/paper/PYT7RCDG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04794&json=true","fetch_graph":"https://pith.science/api/pith-number/PYT7RCDGJLCASJJ2MUGMV3B5JP/graph.json","fetch_events":"https://pith.science/api/pith-number/PYT7RCDGJLCASJJ2MUGMV3B5JP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PYT7RCDGJLCASJJ2MUGMV3B5JP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PYT7RCDGJLCASJJ2MUGMV3B5JP/action/storage_attestation","attest_author":"https://pith.science/pith/PYT7RCDGJLCASJJ2MUGMV3B5JP/action/author_attestation","sign_citation":"https://pith.science/pith/PYT7RCDGJLCASJJ2MUGMV3B5JP/action/citation_signature","submit_replication":"https://pith.science/pith/PYT7RCDGJLCASJJ2MUGMV3B5JP/action/replication_record"}},"created_at":"2026-07-05T11:32:54.293583+00:00","updated_at":"2026-07-05T11:32:54.293583+00:00"}