{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:IS2LVL5VCQIKE5AOZCRINCWOFV","short_pith_number":"pith:IS2LVL5V","schema_version":"1.0","canonical_sha256":"44b4baafb51410a2740ec8a2868ace2d6b428e02b51e4c7c0ca301145e43571a","source":{"kind":"arxiv","id":"1812.02769","version":1},"attestation_state":"computed","paper":{"title":"Embedding-reparameterization procedure for manifold-valued latent variables in generative models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Eugene Golikov, Maksim Kretov","submitted_at":"2018-12-06T19:48:05Z","abstract_excerpt":"Conventional prior for Variational Auto-Encoder (VAE) is a Gaussian distribution. Recent works demonstrated that choice of prior distribution affects learning capacity of VAE models. We propose a general technique (embedding-reparameterization procedure, or ER) for introducing arbitrary manifold-valued variables in VAE model. We compare our technique with a conventional VAE on a toy benchmark problem. This is work in progress."},"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":"1812.02769","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-06T19:48:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f3180d0be71f7a237fbd0943ce8243204ef59cd57439af10ab0cb2ffe5cae087","abstract_canon_sha256":"fc63ae54c68275471597a11d52587e4a50252bbdedc062991761cedd48d00a97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:51.897336Z","signature_b64":"YSRFmPjB1zrnwFmxbOGvq0o6pK6u1vY54lEP1eAyAatcNTMrYx+veZy3IXr791/OSzI2S5PZO4mp+3x02xN8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44b4baafb51410a2740ec8a2868ace2d6b428e02b51e4c7c0ca301145e43571a","last_reissued_at":"2026-05-17T23:58:51.896836Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:51.896836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Embedding-reparameterization procedure for manifold-valued latent variables in generative models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Eugene Golikov, Maksim Kretov","submitted_at":"2018-12-06T19:48:05Z","abstract_excerpt":"Conventional prior for Variational Auto-Encoder (VAE) is a Gaussian distribution. Recent works demonstrated that choice of prior distribution affects learning capacity of VAE models. We propose a general technique (embedding-reparameterization procedure, or ER) for introducing arbitrary manifold-valued variables in VAE model. We compare our technique with a conventional VAE on a toy benchmark problem. This is work in progress."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02769","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":""},"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":"1812.02769","created_at":"2026-05-17T23:58:51.896915+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.02769v1","created_at":"2026-05-17T23:58:51.896915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02769","created_at":"2026-05-17T23:58:51.896915+00:00"},{"alias_kind":"pith_short_12","alias_value":"IS2LVL5VCQIK","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"IS2LVL5VCQIKE5AO","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"IS2LVL5V","created_at":"2026-05-18T12:32:31.084164+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/IS2LVL5VCQIKE5AOZCRINCWOFV","json":"https://pith.science/pith/IS2LVL5VCQIKE5AOZCRINCWOFV.json","graph_json":"https://pith.science/api/pith-number/IS2LVL5VCQIKE5AOZCRINCWOFV/graph.json","events_json":"https://pith.science/api/pith-number/IS2LVL5VCQIKE5AOZCRINCWOFV/events.json","paper":"https://pith.science/paper/IS2LVL5V"},"agent_actions":{"view_html":"https://pith.science/pith/IS2LVL5VCQIKE5AOZCRINCWOFV","download_json":"https://pith.science/pith/IS2LVL5VCQIKE5AOZCRINCWOFV.json","view_paper":"https://pith.science/paper/IS2LVL5V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.02769&json=true","fetch_graph":"https://pith.science/api/pith-number/IS2LVL5VCQIKE5AOZCRINCWOFV/graph.json","fetch_events":"https://pith.science/api/pith-number/IS2LVL5VCQIKE5AOZCRINCWOFV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IS2LVL5VCQIKE5AOZCRINCWOFV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IS2LVL5VCQIKE5AOZCRINCWOFV/action/storage_attestation","attest_author":"https://pith.science/pith/IS2LVL5VCQIKE5AOZCRINCWOFV/action/author_attestation","sign_citation":"https://pith.science/pith/IS2LVL5VCQIKE5AOZCRINCWOFV/action/citation_signature","submit_replication":"https://pith.science/pith/IS2LVL5VCQIKE5AOZCRINCWOFV/action/replication_record"}},"created_at":"2026-05-17T23:58:51.896915+00:00","updated_at":"2026-05-17T23:58:51.896915+00:00"}