{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DZSB5MN4NBEVRKCGSLWVCX4QYY","short_pith_number":"pith:DZSB5MN4","schema_version":"1.0","canonical_sha256":"1e641eb1bc684958a84692ed515f90c61d60e4b8c65f434cbb72442e39173630","source":{"kind":"arxiv","id":"2102.03151","version":1},"attestation_state":"computed","paper":{"title":"Reducing the Amortization Gap in Variational Autoencoders: A Bayesian Random Function Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Minyoung Kim, Vladimir Pavlovic","submitted_at":"2021-02-05T13:01:12Z","abstract_excerpt":"Variational autoencoder (VAE) is a very successful generative model whose key element is the so called amortized inference network, which can perform test time inference using a single feed forward pass. Unfortunately, this comes at the cost of degraded accuracy in posterior approximation, often underperforming the instance-wise variational optimization. Although the latest semi-amortized approaches mitigate the issue by performing a few variational optimization updates starting from the VAE's amortized inference output, they inherently suffer from computational overhead for inference at test "},"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":"2102.03151","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-05T13:01:12Z","cross_cats_sorted":[],"title_canon_sha256":"168548abd266f369c6debe968e453c9998a164d8b37772588df6d1a4cfc1e0a6","abstract_canon_sha256":"a013b762ebfc7074bcb6aff54e890ebf1ef4c6c73a147b20df05ff7a0b1f8fe7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:13:06.279774Z","signature_b64":"KU9gQ+NoXrNbkWMGYO4Zpc3CbVjfkUqLYMbYjVBICG2rNXoPKPluGtLX7iTS9mVP+1mOnxSJEDDjfj7n7iAlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e641eb1bc684958a84692ed515f90c61d60e4b8c65f434cbb72442e39173630","last_reissued_at":"2026-07-05T02:13:06.279203Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:13:06.279203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reducing the Amortization Gap in Variational Autoencoders: A Bayesian Random Function Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Minyoung Kim, Vladimir Pavlovic","submitted_at":"2021-02-05T13:01:12Z","abstract_excerpt":"Variational autoencoder (VAE) is a very successful generative model whose key element is the so called amortized inference network, which can perform test time inference using a single feed forward pass. Unfortunately, this comes at the cost of degraded accuracy in posterior approximation, often underperforming the instance-wise variational optimization. Although the latest semi-amortized approaches mitigate the issue by performing a few variational optimization updates starting from the VAE's amortized inference output, they inherently suffer from computational overhead for inference at test "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.03151","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2102.03151/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":"2102.03151","created_at":"2026-07-05T02:13:06.279262+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.03151v1","created_at":"2026-07-05T02:13:06.279262+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.03151","created_at":"2026-07-05T02:13:06.279262+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZSB5MN4NBEV","created_at":"2026-07-05T02:13:06.279262+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZSB5MN4NBEVRKCG","created_at":"2026-07-05T02:13:06.279262+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZSB5MN4","created_at":"2026-07-05T02:13:06.279262+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06796","citing_title":"Instance-Adaptive Parametrization for Amortized Variational Inference","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DZSB5MN4NBEVRKCGSLWVCX4QYY","json":"https://pith.science/pith/DZSB5MN4NBEVRKCGSLWVCX4QYY.json","graph_json":"https://pith.science/api/pith-number/DZSB5MN4NBEVRKCGSLWVCX4QYY/graph.json","events_json":"https://pith.science/api/pith-number/DZSB5MN4NBEVRKCGSLWVCX4QYY/events.json","paper":"https://pith.science/paper/DZSB5MN4"},"agent_actions":{"view_html":"https://pith.science/pith/DZSB5MN4NBEVRKCGSLWVCX4QYY","download_json":"https://pith.science/pith/DZSB5MN4NBEVRKCGSLWVCX4QYY.json","view_paper":"https://pith.science/paper/DZSB5MN4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.03151&json=true","fetch_graph":"https://pith.science/api/pith-number/DZSB5MN4NBEVRKCGSLWVCX4QYY/graph.json","fetch_events":"https://pith.science/api/pith-number/DZSB5MN4NBEVRKCGSLWVCX4QYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZSB5MN4NBEVRKCGSLWVCX4QYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZSB5MN4NBEVRKCGSLWVCX4QYY/action/storage_attestation","attest_author":"https://pith.science/pith/DZSB5MN4NBEVRKCGSLWVCX4QYY/action/author_attestation","sign_citation":"https://pith.science/pith/DZSB5MN4NBEVRKCGSLWVCX4QYY/action/citation_signature","submit_replication":"https://pith.science/pith/DZSB5MN4NBEVRKCGSLWVCX4QYY/action/replication_record"}},"created_at":"2026-07-05T02:13:06.279262+00:00","updated_at":"2026-07-05T02:13:06.279262+00:00"}