{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:D7SXAOL64UV2YBTAXXWWZCCDFD","short_pith_number":"pith:D7SXAOL6","schema_version":"1.0","canonical_sha256":"1fe570397ee52bac0660bded6c884328ff5b24ed72d5f63e0430d12f5395b372","source":{"kind":"arxiv","id":"2304.12141","version":2},"attestation_state":"computed","paper":{"title":"Variational Diffusion Auto-encoder: Latent Space Extraction from Pre-trained Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Carola-Bibiane Sch\\\"onlieb, Georgios Batzolis, Jan Stanczuk","submitted_at":"2023-04-24T14:44:47Z","abstract_excerpt":"As a widely recognized approach to deep generative modeling, Variational Auto-Encoders (VAEs) still face challenges with the quality of generated images, often presenting noticeable blurriness. This issue stems from the unrealistic assumption that approximates the conditional data distribution, $p(\\textbf{x} | \\textbf{z})$, as an isotropic Gaussian. In this paper, we propose a novel solution to address these issues. We illustrate how one can extract a latent space from a pre-existing diffusion model by optimizing an encoder to maximize the marginal data log-likelihood. Furthermore, we demonstr"},"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":"2304.12141","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-24T14:44:47Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"08295f4b7a86a8821bf3004420319f7bdea60d4be80f5a1cb8e91918f752d522","abstract_canon_sha256":"8aa3f5fd9aeaa6d9a9d7882a3e59a3324e44e30abf0f043e46899ffe64692026"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:33.012013Z","signature_b64":"eWrnWsdwneBeQAp+zi7mlnOowEefXhnOsT3QxStfk6egbEByaQPvB8aSJH+Cp2CbQsdXU0N+hv91d1mDX/CrBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fe570397ee52bac0660bded6c884328ff5b24ed72d5f63e0430d12f5395b372","last_reissued_at":"2026-07-05T06:11:33.011561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:33.011561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Diffusion Auto-encoder: Latent Space Extraction from Pre-trained Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Carola-Bibiane Sch\\\"onlieb, Georgios Batzolis, Jan Stanczuk","submitted_at":"2023-04-24T14:44:47Z","abstract_excerpt":"As a widely recognized approach to deep generative modeling, Variational Auto-Encoders (VAEs) still face challenges with the quality of generated images, often presenting noticeable blurriness. This issue stems from the unrealistic assumption that approximates the conditional data distribution, $p(\\textbf{x} | \\textbf{z})$, as an isotropic Gaussian. In this paper, we propose a novel solution to address these issues. We illustrate how one can extract a latent space from a pre-existing diffusion model by optimizing an encoder to maximize the marginal data log-likelihood. Furthermore, we demonstr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.12141","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/2304.12141/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":"2304.12141","created_at":"2026-07-05T06:11:33.011618+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.12141v2","created_at":"2026-07-05T06:11:33.011618+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.12141","created_at":"2026-07-05T06:11:33.011618+00:00"},{"alias_kind":"pith_short_12","alias_value":"D7SXAOL64UV2","created_at":"2026-07-05T06:11:33.011618+00:00"},{"alias_kind":"pith_short_16","alias_value":"D7SXAOL64UV2YBTA","created_at":"2026-07-05T06:11:33.011618+00:00"},{"alias_kind":"pith_short_8","alias_value":"D7SXAOL6","created_at":"2026-07-05T06:11:33.011618+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/D7SXAOL64UV2YBTAXXWWZCCDFD","json":"https://pith.science/pith/D7SXAOL64UV2YBTAXXWWZCCDFD.json","graph_json":"https://pith.science/api/pith-number/D7SXAOL64UV2YBTAXXWWZCCDFD/graph.json","events_json":"https://pith.science/api/pith-number/D7SXAOL64UV2YBTAXXWWZCCDFD/events.json","paper":"https://pith.science/paper/D7SXAOL6"},"agent_actions":{"view_html":"https://pith.science/pith/D7SXAOL64UV2YBTAXXWWZCCDFD","download_json":"https://pith.science/pith/D7SXAOL64UV2YBTAXXWWZCCDFD.json","view_paper":"https://pith.science/paper/D7SXAOL6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.12141&json=true","fetch_graph":"https://pith.science/api/pith-number/D7SXAOL64UV2YBTAXXWWZCCDFD/graph.json","fetch_events":"https://pith.science/api/pith-number/D7SXAOL64UV2YBTAXXWWZCCDFD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D7SXAOL64UV2YBTAXXWWZCCDFD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D7SXAOL64UV2YBTAXXWWZCCDFD/action/storage_attestation","attest_author":"https://pith.science/pith/D7SXAOL64UV2YBTAXXWWZCCDFD/action/author_attestation","sign_citation":"https://pith.science/pith/D7SXAOL64UV2YBTAXXWWZCCDFD/action/citation_signature","submit_replication":"https://pith.science/pith/D7SXAOL64UV2YBTAXXWWZCCDFD/action/replication_record"}},"created_at":"2026-07-05T06:11:33.011618+00:00","updated_at":"2026-07-05T06:11:33.011618+00:00"}