{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:3IZ6DQ57CU3AUBDRB5ITVVYIG3","short_pith_number":"pith:3IZ6DQ57","canonical_record":{"source":{"id":"1902.10294","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-27T01:34:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9a297c0f3797b855753bcc2653705f9cb8d87ce87ea8ec8314c93451e2424bd7","abstract_canon_sha256":"dc4357a1545a25053222835ea1ce4f3f0d02c24ebf346588fd1c95014d692dae"},"schema_version":"1.0"},"canonical_sha256":"da33e1c3bf15360a04710f513ad70836d3bde5eef5850908f4127c12524240f9","source":{"kind":"arxiv","id":"1902.10294","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.10294","created_at":"2026-05-17T23:52:31Z"},{"alias_kind":"arxiv_version","alias_value":"1902.10294v1","created_at":"2026-05-17T23:52:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10294","created_at":"2026-05-17T23:52:31Z"},{"alias_kind":"pith_short_12","alias_value":"3IZ6DQ57CU3A","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"3IZ6DQ57CU3AUBDR","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"3IZ6DQ57","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:3IZ6DQ57CU3AUBDRB5ITVVYIG3","target":"record","payload":{"canonical_record":{"source":{"id":"1902.10294","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-27T01:34:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9a297c0f3797b855753bcc2653705f9cb8d87ce87ea8ec8314c93451e2424bd7","abstract_canon_sha256":"dc4357a1545a25053222835ea1ce4f3f0d02c24ebf346588fd1c95014d692dae"},"schema_version":"1.0"},"canonical_sha256":"da33e1c3bf15360a04710f513ad70836d3bde5eef5850908f4127c12524240f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:31.274043Z","signature_b64":"sIn7X9fV7f6GRH6p7sp9SL4r+HiPTzoam+BZH1LxA9d++73CrwHNpkEZWGc29WioDF3DPRZHvQah/BZoFi4GAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da33e1c3bf15360a04710f513ad70836d3bde5eef5850908f4127c12524240f9","last_reissued_at":"2026-05-17T23:52:31.273585Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:31.273585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.10294","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:52:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v51Lz7Z08HYjfNxwVchBuW8C4PKBiBF7i6onDJmkuTUt/j2yBCLkCSM3uKCmAWXJG6NAidkBoQ4Ha31XI0cwBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T17:52:33.931522Z"},"content_sha256":"4b0ff89e0cc2edf2754f73f43a2af8476812138b256e75cc0f41c5529b9e062e","schema_version":"1.0","event_id":"sha256:4b0ff89e0cc2edf2754f73f43a2af8476812138b256e75cc0f41c5529b9e062e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:3IZ6DQ57CU3AUBDRB5ITVVYIG3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Variational Autoencoders with Buffered Stochastic Variational Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hung H. Bui, Jay Whang, Rui Shu, Stefano Ermon","submitted_at":"2019-02-27T01:34:57Z","abstract_excerpt":"The recognition network in deep latent variable models such as variational autoencoders (VAEs) relies on amortized inference for efficient posterior approximation that can scale up to large datasets. However, this technique has also been demonstrated to select suboptimal variational parameters, often resulting in considerable additional error called the amortization gap. To close the amortization gap and improve the training of the generative model, recent works have introduced an additional refinement step that applies stochastic variational inference (SVI) to improve upon the variational par"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10294","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:52:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"st0HVv+X+7v0YCIofj91eiauaREHV656mZP/saTL4lmtwrIzBta08mwkcagoxCzo+vNgYk78p7N28o2JOMeQAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T17:52:33.931875Z"},"content_sha256":"99051b51dd8cf371638b6aaf73d68e86b1e56f729947533eb6df2d42059d3924","schema_version":"1.0","event_id":"sha256:99051b51dd8cf371638b6aaf73d68e86b1e56f729947533eb6df2d42059d3924"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3IZ6DQ57CU3AUBDRB5ITVVYIG3/bundle.json","state_url":"https://pith.science/pith/3IZ6DQ57CU3AUBDRB5ITVVYIG3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3IZ6DQ57CU3AUBDRB5ITVVYIG3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-02T17:52:33Z","links":{"resolver":"https://pith.science/pith/3IZ6DQ57CU3AUBDRB5ITVVYIG3","bundle":"https://pith.science/pith/3IZ6DQ57CU3AUBDRB5ITVVYIG3/bundle.json","state":"https://pith.science/pith/3IZ6DQ57CU3AUBDRB5ITVVYIG3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3IZ6DQ57CU3AUBDRB5ITVVYIG3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:3IZ6DQ57CU3AUBDRB5ITVVYIG3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"dc4357a1545a25053222835ea1ce4f3f0d02c24ebf346588fd1c95014d692dae","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-27T01:34:57Z","title_canon_sha256":"9a297c0f3797b855753bcc2653705f9cb8d87ce87ea8ec8314c93451e2424bd7"},"schema_version":"1.0","source":{"id":"1902.10294","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.10294","created_at":"2026-05-17T23:52:31Z"},{"alias_kind":"arxiv_version","alias_value":"1902.10294v1","created_at":"2026-05-17T23:52:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10294","created_at":"2026-05-17T23:52:31Z"},{"alias_kind":"pith_short_12","alias_value":"3IZ6DQ57CU3A","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"3IZ6DQ57CU3AUBDR","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"3IZ6DQ57","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:99051b51dd8cf371638b6aaf73d68e86b1e56f729947533eb6df2d42059d3924","target":"graph","created_at":"2026-05-17T23:52:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"The recognition network in deep latent variable models such as variational autoencoders (VAEs) relies on amortized inference for efficient posterior approximation that can scale up to large datasets. However, this technique has also been demonstrated to select suboptimal variational parameters, often resulting in considerable additional error called the amortization gap. To close the amortization gap and improve the training of the generative model, recent works have introduced an additional refinement step that applies stochastic variational inference (SVI) to improve upon the variational par","authors_text":"Hung H. Bui, Jay Whang, Rui Shu, Stefano Ermon","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-27T01:34:57Z","title":"Training Variational Autoencoders with Buffered Stochastic Variational Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10294","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4b0ff89e0cc2edf2754f73f43a2af8476812138b256e75cc0f41c5529b9e062e","target":"record","created_at":"2026-05-17T23:52:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"dc4357a1545a25053222835ea1ce4f3f0d02c24ebf346588fd1c95014d692dae","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-27T01:34:57Z","title_canon_sha256":"9a297c0f3797b855753bcc2653705f9cb8d87ce87ea8ec8314c93451e2424bd7"},"schema_version":"1.0","source":{"id":"1902.10294","kind":"arxiv","version":1}},"canonical_sha256":"da33e1c3bf15360a04710f513ad70836d3bde5eef5850908f4127c12524240f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da33e1c3bf15360a04710f513ad70836d3bde5eef5850908f4127c12524240f9","first_computed_at":"2026-05-17T23:52:31.273585Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:31.273585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sIn7X9fV7f6GRH6p7sp9SL4r+HiPTzoam+BZH1LxA9d++73CrwHNpkEZWGc29WioDF3DPRZHvQah/BZoFi4GAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:31.274043Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.10294","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b0ff89e0cc2edf2754f73f43a2af8476812138b256e75cc0f41c5529b9e062e","sha256:99051b51dd8cf371638b6aaf73d68e86b1e56f729947533eb6df2d42059d3924"],"state_sha256":"38a86916c77be0d4a58ab440d7a3714f6ba048a8842ca1619360c4394d89c7e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AMnjBR52SSUKuYDmX9NRy7EjKHaxyzE6grLJyE/fz4In6zCrNmz4YbUTireW45f7n8geCMtjGK0CNM7IvoIRDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T17:52:33.933910Z","bundle_sha256":"8620990c20b06be1703fa25475c0fce38c339eb07bb2781cb8b22e9a19c9af37"}}