{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4EI4VLCBANWLUSGCQ2IK5OWS5R","short_pith_number":"pith:4EI4VLCB","schema_version":"1.0","canonical_sha256":"e111caac41036cba48c28690aebad2ec51e8c68c8d8dfb73172e00805bed6f25","source":{"kind":"arxiv","id":"1901.08991","version":2},"attestation_state":"computed","paper":{"title":"Diffusion Variational Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jacobus W. Portegies, Luis A. P\\'erez Rey, Vlado Menkovski","submitted_at":"2019-01-25T17:10:25Z","abstract_excerpt":"A standard Variational Autoencoder, with a Euclidean latent space, is structurally incapable of capturing topological properties of certain datasets. To remove topological obstructions, we introduce Diffusion Variational Autoencoders with arbitrary manifolds as a latent space. A Diffusion Variational Autoencoder uses transition kernels of Brownian motion on the manifold. In particular, it uses properties of the Brownian motion to implement the reparametrization trick and fast approximations to the KL divergence. We show that the Diffusion Variational Autoencoder is capable of capturing topolog"},"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":"1901.08991","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-25T17:10:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3381c00067cdd2fdff5dbb09be10c0b059382f00c44c27ba3fa2d24302f6d2a1","abstract_canon_sha256":"8c37acef81a3107e26a70f60526a8524179b5dba54de4ebbc83a7e66e3729580"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:59.346768Z","signature_b64":"gaKLER6xeQx74zhKJK++fpZ039Y75Y6SoYfxNl22eSUYanfgF8/4os1WJ0smf9QTNfXF5TlDegw8VjNRBNxzAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e111caac41036cba48c28690aebad2ec51e8c68c8d8dfb73172e00805bed6f25","last_reissued_at":"2026-07-05T04:11:59.346362Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:59.346362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Variational Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jacobus W. Portegies, Luis A. P\\'erez Rey, Vlado Menkovski","submitted_at":"2019-01-25T17:10:25Z","abstract_excerpt":"A standard Variational Autoencoder, with a Euclidean latent space, is structurally incapable of capturing topological properties of certain datasets. To remove topological obstructions, we introduce Diffusion Variational Autoencoders with arbitrary manifolds as a latent space. A Diffusion Variational Autoencoder uses transition kernels of Brownian motion on the manifold. In particular, it uses properties of the Brownian motion to implement the reparametrization trick and fast approximations to the KL divergence. We show that the Diffusion Variational Autoencoder is capable of capturing topolog"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08991","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/1901.08991/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":"1901.08991","created_at":"2026-07-05T04:11:59.346423+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.08991v2","created_at":"2026-07-05T04:11:59.346423+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08991","created_at":"2026-07-05T04:11:59.346423+00:00"},{"alias_kind":"pith_short_12","alias_value":"4EI4VLCBANWL","created_at":"2026-07-05T04:11:59.346423+00:00"},{"alias_kind":"pith_short_16","alias_value":"4EI4VLCBANWLUSGC","created_at":"2026-07-05T04:11:59.346423+00:00"},{"alias_kind":"pith_short_8","alias_value":"4EI4VLCB","created_at":"2026-07-05T04:11:59.346423+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12187","citing_title":"Characterizing Neural Manifolds' Properties and Curvatures using Normalizing Flows","ref_index":59,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4EI4VLCBANWLUSGCQ2IK5OWS5R","json":"https://pith.science/pith/4EI4VLCBANWLUSGCQ2IK5OWS5R.json","graph_json":"https://pith.science/api/pith-number/4EI4VLCBANWLUSGCQ2IK5OWS5R/graph.json","events_json":"https://pith.science/api/pith-number/4EI4VLCBANWLUSGCQ2IK5OWS5R/events.json","paper":"https://pith.science/paper/4EI4VLCB"},"agent_actions":{"view_html":"https://pith.science/pith/4EI4VLCBANWLUSGCQ2IK5OWS5R","download_json":"https://pith.science/pith/4EI4VLCBANWLUSGCQ2IK5OWS5R.json","view_paper":"https://pith.science/paper/4EI4VLCB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.08991&json=true","fetch_graph":"https://pith.science/api/pith-number/4EI4VLCBANWLUSGCQ2IK5OWS5R/graph.json","fetch_events":"https://pith.science/api/pith-number/4EI4VLCBANWLUSGCQ2IK5OWS5R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4EI4VLCBANWLUSGCQ2IK5OWS5R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4EI4VLCBANWLUSGCQ2IK5OWS5R/action/storage_attestation","attest_author":"https://pith.science/pith/4EI4VLCBANWLUSGCQ2IK5OWS5R/action/author_attestation","sign_citation":"https://pith.science/pith/4EI4VLCBANWLUSGCQ2IK5OWS5R/action/citation_signature","submit_replication":"https://pith.science/pith/4EI4VLCBANWLUSGCQ2IK5OWS5R/action/replication_record"}},"created_at":"2026-07-05T04:11:59.346423+00:00","updated_at":"2026-07-05T04:11:59.346423+00:00"}