{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:47EQM3X6Q7TIBNMGEF55H3QMXE","short_pith_number":"pith:47EQM3X6","schema_version":"1.0","canonical_sha256":"e7c9066efe87e680b586217bd3ee0cb9094d325188d6cb33ef7f5f2cbdb530eb","source":{"kind":"arxiv","id":"1705.07120","version":5},"attestation_state":"computed","paper":{"title":"VAE with a VampPrior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jakub M. Tomczak, Max Welling","submitted_at":"2017-05-19T10:07:00Z","abstract_excerpt":"Many different methods to train deep generative models have been introduced in the past. In this paper, we propose to extend the variational auto-encoder (VAE) framework with a new type of prior which we call \"Variational Mixture of Posteriors\" prior, or VampPrior for short. The VampPrior consists of a mixture distribution (e.g., a mixture of Gaussians) with components given by variational posteriors conditioned on learnable pseudo-inputs. We further extend this prior to a two layer hierarchical model and show that this architecture with a coupled prior and posterior, learns significantly bett"},"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":"1705.07120","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-19T10:07:00Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"548e42372f5c25465be54ce0e5cfb32b82f0002fc755840e27e4142a7fdfe935","abstract_canon_sha256":"5728df72c720e9cf3f89e0f65e0f8614d2bdba6e5da1f59fee4ff904ec1b74e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:39.865466Z","signature_b64":"Jdalb2gRh5wVp+EuI4yHXrGSE/Iki8G+pZMspIzrSQkSu9MX/N2yk4mTrBjuBERn0MMRe4GnJltv/Zb8P1N/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7c9066efe87e680b586217bd3ee0cb9094d325188d6cb33ef7f5f2cbdb530eb","last_reissued_at":"2026-05-18T00:22:39.865101Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:39.865101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VAE with a VampPrior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jakub M. Tomczak, Max Welling","submitted_at":"2017-05-19T10:07:00Z","abstract_excerpt":"Many different methods to train deep generative models have been introduced in the past. In this paper, we propose to extend the variational auto-encoder (VAE) framework with a new type of prior which we call \"Variational Mixture of Posteriors\" prior, or VampPrior for short. The VampPrior consists of a mixture distribution (e.g., a mixture of Gaussians) with components given by variational posteriors conditioned on learnable pseudo-inputs. We further extend this prior to a two layer hierarchical model and show that this architecture with a coupled prior and posterior, learns significantly bett"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07120","kind":"arxiv","version":5},"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":"1705.07120","created_at":"2026-05-18T00:22:39.865159+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.07120v5","created_at":"2026-05-18T00:22:39.865159+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07120","created_at":"2026-05-18T00:22:39.865159+00:00"},{"alias_kind":"pith_short_12","alias_value":"47EQM3X6Q7TI","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"47EQM3X6Q7TIBNMG","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"47EQM3X6","created_at":"2026-05-18T12:30:58.224056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.15471","citing_title":"CITYMPC: A Large-Scale Physics-Informed Benchmark and Tool for Generative Complete Multipath Wireless Channel Modeling","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/47EQM3X6Q7TIBNMGEF55H3QMXE","json":"https://pith.science/pith/47EQM3X6Q7TIBNMGEF55H3QMXE.json","graph_json":"https://pith.science/api/pith-number/47EQM3X6Q7TIBNMGEF55H3QMXE/graph.json","events_json":"https://pith.science/api/pith-number/47EQM3X6Q7TIBNMGEF55H3QMXE/events.json","paper":"https://pith.science/paper/47EQM3X6"},"agent_actions":{"view_html":"https://pith.science/pith/47EQM3X6Q7TIBNMGEF55H3QMXE","download_json":"https://pith.science/pith/47EQM3X6Q7TIBNMGEF55H3QMXE.json","view_paper":"https://pith.science/paper/47EQM3X6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.07120&json=true","fetch_graph":"https://pith.science/api/pith-number/47EQM3X6Q7TIBNMGEF55H3QMXE/graph.json","fetch_events":"https://pith.science/api/pith-number/47EQM3X6Q7TIBNMGEF55H3QMXE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/47EQM3X6Q7TIBNMGEF55H3QMXE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/47EQM3X6Q7TIBNMGEF55H3QMXE/action/storage_attestation","attest_author":"https://pith.science/pith/47EQM3X6Q7TIBNMGEF55H3QMXE/action/author_attestation","sign_citation":"https://pith.science/pith/47EQM3X6Q7TIBNMGEF55H3QMXE/action/citation_signature","submit_replication":"https://pith.science/pith/47EQM3X6Q7TIBNMGEF55H3QMXE/action/replication_record"}},"created_at":"2026-05-18T00:22:39.865159+00:00","updated_at":"2026-05-18T00:22:39.865159+00:00"}