{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:R7DCYFSHVBAPJDFLT6QM7WKTJ4","short_pith_number":"pith:R7DCYFSH","schema_version":"1.0","canonical_sha256":"8fc62c1647a840f48cab9fa0cfd9534f27d15b1760d700e013a4e7bd67182430","source":{"kind":"arxiv","id":"2206.05564","version":2},"attestation_state":"computed","paper":{"title":"gDDIM: Generalized denoising diffusion implicit models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Molei Tao, Qinsheng Zhang, Yongxin Chen","submitted_at":"2022-06-11T16:57:23Z","abstract_excerpt":"Our goal is to extend the denoising diffusion implicit model (DDIM) to general diffusion models~(DMs) besides isotropic diffusions. Instead of constructing a non-Markov noising process as in the original DDIM, we examine the mechanism of DDIM from a numerical perspective. We discover that the DDIM can be obtained by using some specific approximations of the score when solving the corresponding stochastic differential equation. We present an interpretation of the accelerating effects of DDIM that also explains the advantages of a deterministic sampling scheme over the stochastic one for fast sa"},"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":"2206.05564","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-11T16:57:23Z","cross_cats_sorted":[],"title_canon_sha256":"26e77821b9c3cd22634d6d90a3eab52cf1434ca13a7f16a33e97577634cfd6a7","abstract_canon_sha256":"4c9aa8844c2649e878eda49f75f8e58217d6a1f34687ba795f834a0af5f291bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:53:48.416526Z","signature_b64":"RUa3lquPZid8qTBUaZ6NtdwwFAl2XhsRzNIF7PToh5UL26jvD4/+Y7pf6wcLUDH4ZSd+SZ6wdj3Hkrep3R0MDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fc62c1647a840f48cab9fa0cfd9534f27d15b1760d700e013a4e7bd67182430","last_reissued_at":"2026-07-05T05:53:48.416034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:53:48.416034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"gDDIM: Generalized denoising diffusion implicit models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Molei Tao, Qinsheng Zhang, Yongxin Chen","submitted_at":"2022-06-11T16:57:23Z","abstract_excerpt":"Our goal is to extend the denoising diffusion implicit model (DDIM) to general diffusion models~(DMs) besides isotropic diffusions. Instead of constructing a non-Markov noising process as in the original DDIM, we examine the mechanism of DDIM from a numerical perspective. We discover that the DDIM can be obtained by using some specific approximations of the score when solving the corresponding stochastic differential equation. We present an interpretation of the accelerating effects of DDIM that also explains the advantages of a deterministic sampling scheme over the stochastic one for fast sa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.05564","kind":"arxiv","version":2},"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/2206.05564/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":"2206.05564","created_at":"2026-07-05T05:53:48.416093+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.05564v2","created_at":"2026-07-05T05:53:48.416093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.05564","created_at":"2026-07-05T05:53:48.416093+00:00"},{"alias_kind":"pith_short_12","alias_value":"R7DCYFSHVBAP","created_at":"2026-07-05T05:53:48.416093+00:00"},{"alias_kind":"pith_short_16","alias_value":"R7DCYFSHVBAPJDFL","created_at":"2026-07-05T05:53:48.416093+00:00"},{"alias_kind":"pith_short_8","alias_value":"R7DCYFSH","created_at":"2026-07-05T05:53:48.416093+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2311.04145","citing_title":"I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2511.17031","citing_title":"Energy Scaling Laws for Diffusion Models: Quantifying Compute in Image Generation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2211.01095","citing_title":"DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2211.01324","citing_title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2209.03003","citing_title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17673","citing_title":"Grokking of Diffusion Models: Case Study on Modular Addition","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R7DCYFSHVBAPJDFLT6QM7WKTJ4","json":"https://pith.science/pith/R7DCYFSHVBAPJDFLT6QM7WKTJ4.json","graph_json":"https://pith.science/api/pith-number/R7DCYFSHVBAPJDFLT6QM7WKTJ4/graph.json","events_json":"https://pith.science/api/pith-number/R7DCYFSHVBAPJDFLT6QM7WKTJ4/events.json","paper":"https://pith.science/paper/R7DCYFSH"},"agent_actions":{"view_html":"https://pith.science/pith/R7DCYFSHVBAPJDFLT6QM7WKTJ4","download_json":"https://pith.science/pith/R7DCYFSHVBAPJDFLT6QM7WKTJ4.json","view_paper":"https://pith.science/paper/R7DCYFSH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.05564&json=true","fetch_graph":"https://pith.science/api/pith-number/R7DCYFSHVBAPJDFLT6QM7WKTJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/R7DCYFSHVBAPJDFLT6QM7WKTJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R7DCYFSHVBAPJDFLT6QM7WKTJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R7DCYFSHVBAPJDFLT6QM7WKTJ4/action/storage_attestation","attest_author":"https://pith.science/pith/R7DCYFSHVBAPJDFLT6QM7WKTJ4/action/author_attestation","sign_citation":"https://pith.science/pith/R7DCYFSHVBAPJDFLT6QM7WKTJ4/action/citation_signature","submit_replication":"https://pith.science/pith/R7DCYFSHVBAPJDFLT6QM7WKTJ4/action/replication_record"}},"created_at":"2026-07-05T05:53:48.416093+00:00","updated_at":"2026-07-05T05:53:48.416093+00:00"}