{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VBA26UM7XKZYXG2D4HXYQW6JDQ","short_pith_number":"pith:VBA26UM7","schema_version":"1.0","canonical_sha256":"a841af519fbab38b9b43e1ef885bc91c0b29086f5669175c1ffe955d5d9952b7","source":{"kind":"arxiv","id":"2605.13175","version":1},"attestation_state":"computed","paper":{"title":"Do Heavy Tails Help Diffusion? On the Subtle Trade-off Between Initialization and Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Heavy-tailed noise makes statistical estimation harder in diffusion models than Gaussian noise.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antonio Ocello, Hamza Cherkaoui, H\\'el\\`ene Halconruy","submitted_at":"2026-05-13T08:37:59Z","abstract_excerpt":"Recent works have proposed incorporating heavy-tailed (HT) noise into diffusion- and flow-based generative models, with the goals of better recovering the tails of target distributions and improving generative diversity. This motivation is intuitive: if the data are heavy-tailed, HT noise may appear better matched than light-tailed (LT) Gaussian noise. However, replacing Gaussian noise by HT noise also changes the underlying estimation problem. In this paper, we revisit this paradigm through a combined theoretical and empirical study, establishing sampling-error bounds for two representative d"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.13175","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T08:37:59Z","cross_cats_sorted":[],"title_canon_sha256":"767685429e53469c55d11cbbbfb667cad6f9e6cc26032a48ac1876b5628df505","abstract_canon_sha256":"112280043ddbcafb9f0b569126ba471a7d61a44638d7c5da1ea8ff3b70772e88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:08:56.486202Z","signature_b64":"61zkCB+x8lTBzltIF9nA57ASIPAfx216xYrRbvTZKCMiZuNN12XUhvQfS+KEGfyKDdfuebMTPtXhUo/zxfVPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a841af519fbab38b9b43e1ef885bc91c0b29086f5669175c1ffe955d5d9952b7","last_reissued_at":"2026-05-18T03:08:56.485470Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:08:56.485470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Heavy Tails Help Diffusion? On the Subtle Trade-off Between Initialization and Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Heavy-tailed noise makes statistical estimation harder in diffusion models than Gaussian noise.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antonio Ocello, Hamza Cherkaoui, H\\'el\\`ene Halconruy","submitted_at":"2026-05-13T08:37:59Z","abstract_excerpt":"Recent works have proposed incorporating heavy-tailed (HT) noise into diffusion- and flow-based generative models, with the goals of better recovering the tails of target distributions and improving generative diversity. This motivation is intuitive: if the data are heavy-tailed, HT noise may appear better matched than light-tailed (LT) Gaussian noise. However, replacing Gaussian noise by HT noise also changes the underlying estimation problem. In this paper, we revisit this paradigm through a combined theoretical and empirical study, establishing sampling-error bounds for two representative d"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We show that HT noise makes the statistical estimation problem harder, leading to less favorable sampling-error bounds.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the derived sampling-error bounds for the two representative diffusion models are tight enough to reflect practical performance differences between HT and LT noise across the tested regimes.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Heavy-tailed noise in diffusion models leads to less favorable sampling-error bounds than light-tailed Gaussian noise by making the underlying statistical estimation problem harder.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Heavy-tailed noise makes statistical estimation harder in diffusion models than Gaussian noise.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"384378a8dde9f257125ea9755595684e37547bf170fffd90e0b5e784cc8c7c53"},"source":{"id":"2605.13175","kind":"arxiv","version":1},"verdict":{"id":"be39c0f9-5f95-4946-97f3-6e8b52e47314","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:07:39.988222Z","strongest_claim":"We show that HT noise makes the statistical estimation problem harder, leading to less favorable sampling-error bounds.","one_line_summary":"Heavy-tailed noise in diffusion models leads to less favorable sampling-error bounds than light-tailed Gaussian noise by making the underlying statistical estimation problem harder.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the derived sampling-error bounds for the two representative diffusion models are tight enough to reflect practical performance differences between HT and LT noise across the tested regimes.","pith_extraction_headline":"Heavy-tailed noise makes statistical estimation harder in diffusion models than Gaussian noise."},"references":{"count":15,"sample":[{"doi":"","year":null,"title":"Initialization-aware score-based diffusion sampling.arXiv preprint arXiv:2603.00772,","work_id":"fe0b9c84-3c6b-4130-9088-13ad868bd075","ref_index":1,"cited_arxiv_id":"2603.00772","is_internal_anchor":true},{"doi":"","year":null,"title":"Diffusion generative models meet compressed sensing, with applications to imaging and finance.arXiv preprint arXiv:2509.03898,","work_id":"98b0239a-3092-41f2-9051-bef7217df386","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1007/978-3-030-52915-4","year":null,"title":"Springer Series in Operations Research and Financial Engineering","work_id":"1dc631c0-8b4f-44e0-8e51-1dd71862305c","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Heavy-tailed diffusion with denoising lévy probabilistic models","work_id":"f1716af4-56e8-4ead-a5ec-365690f50fac","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Lipschitz regularity in Flow Matching and Diffusion Models: sharp sampling rates and functional inequalities","work_id":"4fb70106-c9d6-48e2-9be8-707e4273105e","ref_index":5,"cited_arxiv_id":"2604.06065","is_internal_anchor":true}],"resolved_work":15,"snapshot_sha256":"63a28508f3e127f57b60a157be34b2d2de9ae603f5a066d37730c8ce629d938f","internal_anchors":2},"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":"2605.13175","created_at":"2026-05-18T03:08:56.485593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13175v1","created_at":"2026-05-18T03:08:56.485593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13175","created_at":"2026-05-18T03:08:56.485593+00:00"},{"alias_kind":"pith_short_12","alias_value":"VBA26UM7XKZY","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"VBA26UM7XKZYXG2D","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"VBA26UM7","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VBA26UM7XKZYXG2D4HXYQW6JDQ","json":"https://pith.science/pith/VBA26UM7XKZYXG2D4HXYQW6JDQ.json","graph_json":"https://pith.science/api/pith-number/VBA26UM7XKZYXG2D4HXYQW6JDQ/graph.json","events_json":"https://pith.science/api/pith-number/VBA26UM7XKZYXG2D4HXYQW6JDQ/events.json","paper":"https://pith.science/paper/VBA26UM7"},"agent_actions":{"view_html":"https://pith.science/pith/VBA26UM7XKZYXG2D4HXYQW6JDQ","download_json":"https://pith.science/pith/VBA26UM7XKZYXG2D4HXYQW6JDQ.json","view_paper":"https://pith.science/paper/VBA26UM7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13175&json=true","fetch_graph":"https://pith.science/api/pith-number/VBA26UM7XKZYXG2D4HXYQW6JDQ/graph.json","fetch_events":"https://pith.science/api/pith-number/VBA26UM7XKZYXG2D4HXYQW6JDQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VBA26UM7XKZYXG2D4HXYQW6JDQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VBA26UM7XKZYXG2D4HXYQW6JDQ/action/storage_attestation","attest_author":"https://pith.science/pith/VBA26UM7XKZYXG2D4HXYQW6JDQ/action/author_attestation","sign_citation":"https://pith.science/pith/VBA26UM7XKZYXG2D4HXYQW6JDQ/action/citation_signature","submit_replication":"https://pith.science/pith/VBA26UM7XKZYXG2D4HXYQW6JDQ/action/replication_record"}},"created_at":"2026-05-18T03:08:56.485593+00:00","updated_at":"2026-05-18T03:08:56.485593+00:00"}