{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:IAVBEVMC23DUA3ESFDCXKNFAE7","short_pith_number":"pith:IAVBEVMC","schema_version":"1.0","canonical_sha256":"402a125582d6c7406c9228c57534a027d137b7d330e7ccf1ebeaa37fc1876eb5","source":{"kind":"arxiv","id":"1801.03558","version":3},"attestation_state":"computed","paper":{"title":"Inference Suboptimality in Variational Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chris Cremer, David Duvenaud, Xuechen Li","submitted_at":"2018-01-10T21:24:59Z","abstract_excerpt":"Amortized inference allows latent-variable models trained via variational learning to scale to large datasets. The quality of approximate inference is determined by two factors: a) the capacity of the variational distribution to match the true posterior and b) the ability of the recognition network to produce good variational parameters for each datapoint. We examine approximate inference in variational autoencoders in terms of these factors. We find that divergence from the true posterior is often due to imperfect recognition networks, rather than the limited complexity of the approximating d"},"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":"1801.03558","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-10T21:24:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ab46589fd3e3151862b9de40b1c316f993047bc2dd9066238649bd8341f6dafd","abstract_canon_sha256":"bbb3914ff132f28bc74c7bd0eee3b59584fa6c814851065ad2463065e6346d74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:53.967388Z","signature_b64":"bfyPsNFXzNWiZd7lh/JSRHboi2mq3UyprKyoRYMW7x314XAuDoGQMH/y+/4qHech7GMfnq39vcqoxzw237cyDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"402a125582d6c7406c9228c57534a027d137b7d330e7ccf1ebeaa37fc1876eb5","last_reissued_at":"2026-05-18T00:14:53.966675Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:53.966675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inference Suboptimality in Variational Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chris Cremer, David Duvenaud, Xuechen Li","submitted_at":"2018-01-10T21:24:59Z","abstract_excerpt":"Amortized inference allows latent-variable models trained via variational learning to scale to large datasets. The quality of approximate inference is determined by two factors: a) the capacity of the variational distribution to match the true posterior and b) the ability of the recognition network to produce good variational parameters for each datapoint. We examine approximate inference in variational autoencoders in terms of these factors. We find that divergence from the true posterior is often due to imperfect recognition networks, rather than the limited complexity of the approximating d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.03558","kind":"arxiv","version":3},"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":"1801.03558","created_at":"2026-05-18T00:14:53.966777+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.03558v3","created_at":"2026-05-18T00:14:53.966777+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.03558","created_at":"2026-05-18T00:14:53.966777+00:00"},{"alias_kind":"pith_short_12","alias_value":"IAVBEVMC23DU","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"IAVBEVMC23DUA3ES","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"IAVBEVMC","created_at":"2026-05-18T12:32:28.185984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2006.12024","citing_title":"Bayesian Neural Networks: An Introduction and Survey","ref_index":105,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07513","citing_title":"Tessellations of Semi-Discrete Flow Matching","ref_index":135,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IAVBEVMC23DUA3ESFDCXKNFAE7","json":"https://pith.science/pith/IAVBEVMC23DUA3ESFDCXKNFAE7.json","graph_json":"https://pith.science/api/pith-number/IAVBEVMC23DUA3ESFDCXKNFAE7/graph.json","events_json":"https://pith.science/api/pith-number/IAVBEVMC23DUA3ESFDCXKNFAE7/events.json","paper":"https://pith.science/paper/IAVBEVMC"},"agent_actions":{"view_html":"https://pith.science/pith/IAVBEVMC23DUA3ESFDCXKNFAE7","download_json":"https://pith.science/pith/IAVBEVMC23DUA3ESFDCXKNFAE7.json","view_paper":"https://pith.science/paper/IAVBEVMC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.03558&json=true","fetch_graph":"https://pith.science/api/pith-number/IAVBEVMC23DUA3ESFDCXKNFAE7/graph.json","fetch_events":"https://pith.science/api/pith-number/IAVBEVMC23DUA3ESFDCXKNFAE7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IAVBEVMC23DUA3ESFDCXKNFAE7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IAVBEVMC23DUA3ESFDCXKNFAE7/action/storage_attestation","attest_author":"https://pith.science/pith/IAVBEVMC23DUA3ESFDCXKNFAE7/action/author_attestation","sign_citation":"https://pith.science/pith/IAVBEVMC23DUA3ESFDCXKNFAE7/action/citation_signature","submit_replication":"https://pith.science/pith/IAVBEVMC23DUA3ESFDCXKNFAE7/action/replication_record"}},"created_at":"2026-05-18T00:14:53.966777+00:00","updated_at":"2026-05-18T00:14:53.966777+00:00"}