{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TZXZROHTTD6QPV2BKDIQIXLIDW","short_pith_number":"pith:TZXZROHT","schema_version":"1.0","canonical_sha256":"9e6f98b8f398fd07d74150d1045d681d988e64369f3b9365e9e5df02b3f084ed","source":{"kind":"arxiv","id":"2110.05948","version":1},"attestation_state":"computed","paper":{"title":"Denoising Diffusion Gamma Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.GR","cs.LG","cs.SD","eess.AS","eess.IV"],"primary_cat":"eess.SP","authors_text":"Eliya Nachmani, Lior Wolf, Robin San Roman","submitted_at":"2021-10-10T10:46:31Z","abstract_excerpt":"Generative diffusion processes are an emerging and effective tool for image and speech generation. In the existing methods, the underlying noise distribution of the diffusion process is Gaussian noise. However, fitting distributions with more degrees of freedom could improve the performance of such generative models. In this work, we investigate other types of noise distribution for the diffusion process. Specifically, we introduce the Denoising Diffusion Gamma Model (DDGM) and show that noise from Gamma distribution provides improved results for image and speech generation. Our approach prese"},"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":"2110.05948","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SP","submitted_at":"2021-10-10T10:46:31Z","cross_cats_sorted":["cs.AI","cs.CV","cs.GR","cs.LG","cs.SD","eess.AS","eess.IV"],"title_canon_sha256":"7bd6b6fb80ad594422d9f0136628882d51a1d612436e3e2b3b685e9d24d9858a","abstract_canon_sha256":"a95824de28a0b6d6db6b59cc6520f29fb815b62c8080ec486090bd24a19f9df8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:08.729922Z","signature_b64":"krTMJWLV+l1iul2wsTuR7sQpefTH/n1Jl3KsrEdJ/IVVeIDUA2ZK7aTDFMOzTvo7IET7521D+e5DrVXIfCsJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e6f98b8f398fd07d74150d1045d681d988e64369f3b9365e9e5df02b3f084ed","last_reissued_at":"2026-07-05T03:22:08.729487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:08.729487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Denoising Diffusion Gamma Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.GR","cs.LG","cs.SD","eess.AS","eess.IV"],"primary_cat":"eess.SP","authors_text":"Eliya Nachmani, Lior Wolf, Robin San Roman","submitted_at":"2021-10-10T10:46:31Z","abstract_excerpt":"Generative diffusion processes are an emerging and effective tool for image and speech generation. In the existing methods, the underlying noise distribution of the diffusion process is Gaussian noise. However, fitting distributions with more degrees of freedom could improve the performance of such generative models. In this work, we investigate other types of noise distribution for the diffusion process. Specifically, we introduce the Denoising Diffusion Gamma Model (DDGM) and show that noise from Gamma distribution provides improved results for image and speech generation. Our approach prese"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05948","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/2110.05948/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":"2110.05948","created_at":"2026-07-05T03:22:08.729543+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.05948v1","created_at":"2026-07-05T03:22:08.729543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05948","created_at":"2026-07-05T03:22:08.729543+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZXZROHTTD6Q","created_at":"2026-07-05T03:22:08.729543+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZXZROHTTD6QPV2B","created_at":"2026-07-05T03:22:08.729543+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZXZROHT","created_at":"2026-07-05T03:22:08.729543+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/TZXZROHTTD6QPV2BKDIQIXLIDW","json":"https://pith.science/pith/TZXZROHTTD6QPV2BKDIQIXLIDW.json","graph_json":"https://pith.science/api/pith-number/TZXZROHTTD6QPV2BKDIQIXLIDW/graph.json","events_json":"https://pith.science/api/pith-number/TZXZROHTTD6QPV2BKDIQIXLIDW/events.json","paper":"https://pith.science/paper/TZXZROHT"},"agent_actions":{"view_html":"https://pith.science/pith/TZXZROHTTD6QPV2BKDIQIXLIDW","download_json":"https://pith.science/pith/TZXZROHTTD6QPV2BKDIQIXLIDW.json","view_paper":"https://pith.science/paper/TZXZROHT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.05948&json=true","fetch_graph":"https://pith.science/api/pith-number/TZXZROHTTD6QPV2BKDIQIXLIDW/graph.json","fetch_events":"https://pith.science/api/pith-number/TZXZROHTTD6QPV2BKDIQIXLIDW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZXZROHTTD6QPV2BKDIQIXLIDW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZXZROHTTD6QPV2BKDIQIXLIDW/action/storage_attestation","attest_author":"https://pith.science/pith/TZXZROHTTD6QPV2BKDIQIXLIDW/action/author_attestation","sign_citation":"https://pith.science/pith/TZXZROHTTD6QPV2BKDIQIXLIDW/action/citation_signature","submit_replication":"https://pith.science/pith/TZXZROHTTD6QPV2BKDIQIXLIDW/action/replication_record"}},"created_at":"2026-07-05T03:22:08.729543+00:00","updated_at":"2026-07-05T03:22:08.729543+00:00"}