{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:X6K6BOHM2TCBFDFDXJOMUX3YKK","short_pith_number":"pith:X6K6BOHM","schema_version":"1.0","canonical_sha256":"bf95e0b8ecd4c4128ca3ba5cca5f78528793229cef574a06ec386e4d17fc1718","source":{"kind":"arxiv","id":"2407.18609","version":4},"attestation_state":"computed","paper":{"title":"Heavy-Tailed Diffusion with Denoising L\\'evy Probabilistic Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alain Durmus, Dario Shariatian, Umut Simsekli","submitted_at":"2024-07-26T09:00:18Z","abstract_excerpt":"Exploring noise distributions beyond Gaussian in diffusion models remains an open challenge. While Gaussian-based models succeed within a unified SDE framework, recent studies suggest that heavy-tailed noise distributions, like $\\alpha$-stable distributions, may better handle mode collapse and effectively manage datasets exhibiting class imbalance, heavy tails, or prominent outliers. Recently, Yoon et al.\\ (NeurIPS 2023), presented the L\\'evy-It\\^o model (LIM), directly extending the SDE-based framework to a class of heavy-tailed SDEs, where the injected noise followed an $\\alpha$-stable distr"},"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":"2407.18609","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-26T09:00:18Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"da5c877599bc87018b737111b9eb484cb8e4ccf0cabe12e579d403201498631c","abstract_canon_sha256":"76f1973869c44f34a37b3b533effa1b814198c2508d12f3ba4e3c77f6853dd5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:31.453065Z","signature_b64":"xpudcQlxOLMS86NQjVhjmHv5zoS9XhXcwVAvhUjP9SbBWXLM19L/DgrFBy8aAG89TAWy+eXl3WmMLhBxBkTfCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf95e0b8ecd4c4128ca3ba5cca5f78528793229cef574a06ec386e4d17fc1718","last_reissued_at":"2026-07-05T11:22:31.452500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:31.452500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heavy-Tailed Diffusion with Denoising L\\'evy Probabilistic Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alain Durmus, Dario Shariatian, Umut Simsekli","submitted_at":"2024-07-26T09:00:18Z","abstract_excerpt":"Exploring noise distributions beyond Gaussian in diffusion models remains an open challenge. While Gaussian-based models succeed within a unified SDE framework, recent studies suggest that heavy-tailed noise distributions, like $\\alpha$-stable distributions, may better handle mode collapse and effectively manage datasets exhibiting class imbalance, heavy tails, or prominent outliers. Recently, Yoon et al.\\ (NeurIPS 2023), presented the L\\'evy-It\\^o model (LIM), directly extending the SDE-based framework to a class of heavy-tailed SDEs, where the injected noise followed an $\\alpha$-stable distr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18609","kind":"arxiv","version":4},"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/2407.18609/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":"2407.18609","created_at":"2026-07-05T11:22:31.452565+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.18609v4","created_at":"2026-07-05T11:22:31.452565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18609","created_at":"2026-07-05T11:22:31.452565+00:00"},{"alias_kind":"pith_short_12","alias_value":"X6K6BOHM2TCB","created_at":"2026-07-05T11:22:31.452565+00:00"},{"alias_kind":"pith_short_16","alias_value":"X6K6BOHM2TCBFDFD","created_at":"2026-07-05T11:22:31.452565+00:00"},{"alias_kind":"pith_short_8","alias_value":"X6K6BOHM","created_at":"2026-07-05T11:22:31.452565+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/X6K6BOHM2TCBFDFDXJOMUX3YKK","json":"https://pith.science/pith/X6K6BOHM2TCBFDFDXJOMUX3YKK.json","graph_json":"https://pith.science/api/pith-number/X6K6BOHM2TCBFDFDXJOMUX3YKK/graph.json","events_json":"https://pith.science/api/pith-number/X6K6BOHM2TCBFDFDXJOMUX3YKK/events.json","paper":"https://pith.science/paper/X6K6BOHM"},"agent_actions":{"view_html":"https://pith.science/pith/X6K6BOHM2TCBFDFDXJOMUX3YKK","download_json":"https://pith.science/pith/X6K6BOHM2TCBFDFDXJOMUX3YKK.json","view_paper":"https://pith.science/paper/X6K6BOHM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.18609&json=true","fetch_graph":"https://pith.science/api/pith-number/X6K6BOHM2TCBFDFDXJOMUX3YKK/graph.json","fetch_events":"https://pith.science/api/pith-number/X6K6BOHM2TCBFDFDXJOMUX3YKK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X6K6BOHM2TCBFDFDXJOMUX3YKK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X6K6BOHM2TCBFDFDXJOMUX3YKK/action/storage_attestation","attest_author":"https://pith.science/pith/X6K6BOHM2TCBFDFDXJOMUX3YKK/action/author_attestation","sign_citation":"https://pith.science/pith/X6K6BOHM2TCBFDFDXJOMUX3YKK/action/citation_signature","submit_replication":"https://pith.science/pith/X6K6BOHM2TCBFDFDXJOMUX3YKK/action/replication_record"}},"created_at":"2026-07-05T11:22:31.452565+00:00","updated_at":"2026-07-05T11:22:31.452565+00:00"}