{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5TYCXHRVXRMSXSI7ZIUNFM2ZQM","short_pith_number":"pith:5TYCXHRV","schema_version":"1.0","canonical_sha256":"ecf02b9e35bc592bc91fca28d2b359833cf15bd936df679e848d594732ca1717","source":{"kind":"arxiv","id":"2210.05559","version":2},"attestation_state":"computed","paper":{"title":"Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chen Henry Wu, Fernando De la Torre","submitted_at":"2022-10-11T15:53:52Z","abstract_excerpt":"Diffusion models have achieved unprecedented performance in generative modeling. The commonly-adopted formulation of the latent code of diffusion models is a sequence of gradually denoised samples, as opposed to the simpler (e.g., Gaussian) latent space of GANs, VAEs, and normalizing flows. This paper provides an alternative, Gaussian formulation of the latent space of various diffusion models, as well as an invertible DPM-Encoder that maps images into the latent space. While our formulation is purely based on the definition of diffusion models, we demonstrate several intriguing consequences. "},"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":"2210.05559","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-11T15:53:52Z","cross_cats_sorted":["cs.GR","cs.LG"],"title_canon_sha256":"4cca800f9a76aef24c6209857e467e5696e0c1a63866e00ef9f0468e8b31c4d1","abstract_canon_sha256":"e8c45f1ab4d177012ba082071260216a1cc1011e741803de14a763120d016ee9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:23:12.229080Z","signature_b64":"Zkuu/39X8A1xo5rBXpZH4P6da/cXFt3JLmRT+4S5jCO9cHFaSQ6byoY8LbXjBqCW57ytSGN0FGCgpVDbYL9EAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecf02b9e35bc592bc91fca28d2b359833cf15bd936df679e848d594732ca1717","last_reissued_at":"2026-07-05T05:23:12.228672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:23:12.228672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chen Henry Wu, Fernando De la Torre","submitted_at":"2022-10-11T15:53:52Z","abstract_excerpt":"Diffusion models have achieved unprecedented performance in generative modeling. The commonly-adopted formulation of the latent code of diffusion models is a sequence of gradually denoised samples, as opposed to the simpler (e.g., Gaussian) latent space of GANs, VAEs, and normalizing flows. This paper provides an alternative, Gaussian formulation of the latent space of various diffusion models, as well as an invertible DPM-Encoder that maps images into the latent space. While our formulation is purely based on the definition of diffusion models, we demonstrate several intriguing consequences. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05559","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/2210.05559/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":"2210.05559","created_at":"2026-07-05T05:23:12.228727+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.05559v2","created_at":"2026-07-05T05:23:12.228727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05559","created_at":"2026-07-05T05:23:12.228727+00:00"},{"alias_kind":"pith_short_12","alias_value":"5TYCXHRVXRMS","created_at":"2026-07-05T05:23:12.228727+00:00"},{"alias_kind":"pith_short_16","alias_value":"5TYCXHRVXRMSXSI7","created_at":"2026-07-05T05:23:12.228727+00:00"},{"alias_kind":"pith_short_8","alias_value":"5TYCXHRV","created_at":"2026-07-05T05:23:12.228727+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23679","citing_title":"Semantic Browsing: Controllable Diversity for Image Generation","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2412.08079","citing_title":"Regional climate risk assessment from climate models using probabilistic machine learning","ref_index":134,"is_internal_anchor":false},{"citing_arxiv_id":"2505.09831","citing_title":"IMPLICITSTAINER: Resolution Agnostic Data-Efficient Virtual Staining Using Neural Implicit Functions","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18251","citing_title":"Style-Based Neural Architectures for Real-Time Weather Classification","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5TYCXHRVXRMSXSI7ZIUNFM2ZQM","json":"https://pith.science/pith/5TYCXHRVXRMSXSI7ZIUNFM2ZQM.json","graph_json":"https://pith.science/api/pith-number/5TYCXHRVXRMSXSI7ZIUNFM2ZQM/graph.json","events_json":"https://pith.science/api/pith-number/5TYCXHRVXRMSXSI7ZIUNFM2ZQM/events.json","paper":"https://pith.science/paper/5TYCXHRV"},"agent_actions":{"view_html":"https://pith.science/pith/5TYCXHRVXRMSXSI7ZIUNFM2ZQM","download_json":"https://pith.science/pith/5TYCXHRVXRMSXSI7ZIUNFM2ZQM.json","view_paper":"https://pith.science/paper/5TYCXHRV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.05559&json=true","fetch_graph":"https://pith.science/api/pith-number/5TYCXHRVXRMSXSI7ZIUNFM2ZQM/graph.json","fetch_events":"https://pith.science/api/pith-number/5TYCXHRVXRMSXSI7ZIUNFM2ZQM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5TYCXHRVXRMSXSI7ZIUNFM2ZQM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5TYCXHRVXRMSXSI7ZIUNFM2ZQM/action/storage_attestation","attest_author":"https://pith.science/pith/5TYCXHRVXRMSXSI7ZIUNFM2ZQM/action/author_attestation","sign_citation":"https://pith.science/pith/5TYCXHRVXRMSXSI7ZIUNFM2ZQM/action/citation_signature","submit_replication":"https://pith.science/pith/5TYCXHRVXRMSXSI7ZIUNFM2ZQM/action/replication_record"}},"created_at":"2026-07-05T05:23:12.228727+00:00","updated_at":"2026-07-05T05:23:12.228727+00:00"}