{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ROTDFZR2FK4OAT4JNQ2G7BBY6E","short_pith_number":"pith:ROTDFZR2","schema_version":"1.0","canonical_sha256":"8ba632e63a2ab8e04f896c346f8438f11a36159ed4b83a6bd89efc68057b8560","source":{"kind":"arxiv","id":"1803.05649","version":2},"attestation_state":"computed","paper":{"title":"Sylvester Normalizing Flows for Variational Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Jakub M. Tomczak, Leonard Hasenclever, Max Welling, Rianne van den Berg","submitted_at":"2018-03-15T09:15:14Z","abstract_excerpt":"Variational inference relies on flexible approximate posterior distributions. Normalizing flows provide a general recipe to construct flexible variational posteriors. We introduce Sylvester normalizing flows, which can be seen as a generalization of planar flows. Sylvester normalizing flows remove the well-known single-unit bottleneck from planar flows, making a single transformation much more flexible. We compare the performance of Sylvester normalizing flows against planar flows and inverse autoregressive flows and demonstrate that they compare favorably on several datasets."},"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":"1803.05649","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-15T09:15:14Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ME"],"title_canon_sha256":"2ecde2e8586059bb76ae2f778e4bbae6999004e80ea0d4bcb03336e2ce0eb665","abstract_canon_sha256":"f25cb8908af30652c20c1f6df9d0b05feb174d3e73a96e329688f8ef1aa464bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:09.640666Z","signature_b64":"f4TDKvZeQiJPH3qvrc6ASA6Y9Np3jEO/R75cHoCdak+KEheg5Fxe0bx63aGOdqNULKbkXAeF37Cdeptfy8qHCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ba632e63a2ab8e04f896c346f8438f11a36159ed4b83a6bd89efc68057b8560","last_reissued_at":"2026-05-17T23:53:09.639963Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:09.639963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sylvester Normalizing Flows for Variational Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Jakub M. Tomczak, Leonard Hasenclever, Max Welling, Rianne van den Berg","submitted_at":"2018-03-15T09:15:14Z","abstract_excerpt":"Variational inference relies on flexible approximate posterior distributions. Normalizing flows provide a general recipe to construct flexible variational posteriors. We introduce Sylvester normalizing flows, which can be seen as a generalization of planar flows. Sylvester normalizing flows remove the well-known single-unit bottleneck from planar flows, making a single transformation much more flexible. We compare the performance of Sylvester normalizing flows against planar flows and inverse autoregressive flows and demonstrate that they compare favorably on several datasets."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.05649","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":""},"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":"1803.05649","created_at":"2026-05-17T23:53:09.640059+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.05649v2","created_at":"2026-05-17T23:53:09.640059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.05649","created_at":"2026-05-17T23:53:09.640059+00:00"},{"alias_kind":"pith_short_12","alias_value":"ROTDFZR2FK4O","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"ROTDFZR2FK4OAT4J","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"ROTDFZR2","created_at":"2026-05-18T12:32:50.500415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1806.07366","citing_title":"Neural Ordinary Differential Equations","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ROTDFZR2FK4OAT4JNQ2G7BBY6E","json":"https://pith.science/pith/ROTDFZR2FK4OAT4JNQ2G7BBY6E.json","graph_json":"https://pith.science/api/pith-number/ROTDFZR2FK4OAT4JNQ2G7BBY6E/graph.json","events_json":"https://pith.science/api/pith-number/ROTDFZR2FK4OAT4JNQ2G7BBY6E/events.json","paper":"https://pith.science/paper/ROTDFZR2"},"agent_actions":{"view_html":"https://pith.science/pith/ROTDFZR2FK4OAT4JNQ2G7BBY6E","download_json":"https://pith.science/pith/ROTDFZR2FK4OAT4JNQ2G7BBY6E.json","view_paper":"https://pith.science/paper/ROTDFZR2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.05649&json=true","fetch_graph":"https://pith.science/api/pith-number/ROTDFZR2FK4OAT4JNQ2G7BBY6E/graph.json","fetch_events":"https://pith.science/api/pith-number/ROTDFZR2FK4OAT4JNQ2G7BBY6E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ROTDFZR2FK4OAT4JNQ2G7BBY6E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ROTDFZR2FK4OAT4JNQ2G7BBY6E/action/storage_attestation","attest_author":"https://pith.science/pith/ROTDFZR2FK4OAT4JNQ2G7BBY6E/action/author_attestation","sign_citation":"https://pith.science/pith/ROTDFZR2FK4OAT4JNQ2G7BBY6E/action/citation_signature","submit_replication":"https://pith.science/pith/ROTDFZR2FK4OAT4JNQ2G7BBY6E/action/replication_record"}},"created_at":"2026-05-17T23:53:09.640059+00:00","updated_at":"2026-05-17T23:53:09.640059+00:00"}