{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:5UGE2K3MMEPW7XOGPKKNMW5RFP","short_pith_number":"pith:5UGE2K3M","canonical_record":{"source":{"id":"1805.08913","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-23T00:14:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a41b85040ffc790922dc71a1555f8bdb67677fdb2143f11ed2ce79c2b1a52a6c","abstract_canon_sha256":"aa106c1b900c5c1636691aac8ceac88438703a386a0efa549d16d74fd668889c"},"schema_version":"1.0"},"canonical_sha256":"ed0c4d2b6c611f6fddc67a94d65bb12bf9654c9796a6442a48898389c12cb46d","source":{"kind":"arxiv","id":"1805.08913","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08913","created_at":"2026-05-17T23:56:41Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08913v2","created_at":"2026-05-17T23:56:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08913","created_at":"2026-05-17T23:56:41Z"},{"alias_kind":"pith_short_12","alias_value":"5UGE2K3MMEPW","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5UGE2K3MMEPW7XOG","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5UGE2K3M","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:5UGE2K3MMEPW7XOGPKKNMW5RFP","target":"record","payload":{"canonical_record":{"source":{"id":"1805.08913","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-23T00:14:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a41b85040ffc790922dc71a1555f8bdb67677fdb2143f11ed2ce79c2b1a52a6c","abstract_canon_sha256":"aa106c1b900c5c1636691aac8ceac88438703a386a0efa549d16d74fd668889c"},"schema_version":"1.0"},"canonical_sha256":"ed0c4d2b6c611f6fddc67a94d65bb12bf9654c9796a6442a48898389c12cb46d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:41.330613Z","signature_b64":"rrdM7ISYgAva8nQm3Nd+ovIJ0tY78v5StaOdAmkPOHcNcATPeky+QxtdVe5KOCXl+Q5F1qAukreUa58VbmEECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed0c4d2b6c611f6fddc67a94d65bb12bf9654c9796a6442a48898389c12cb46d","last_reissued_at":"2026-05-17T23:56:41.330002Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:41.330002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.08913","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:56:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B6a39aZpr8nZ4vZYWHchk7TFLN9f24IRbWKeTYrnfRKxKydW9L/rsjjhWVghDSc+ugrico/sWUEpgiNjbCwaBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T21:29:34.840770Z"},"content_sha256":"aeef5d51add2b36ebd8dec400196423b26111f587d931ee233d4b1b0234250dd","schema_version":"1.0","event_id":"sha256:aeef5d51add2b36ebd8dec400196423b26111f587d931ee233d4b1b0234250dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:5UGE2K3MMEPW7XOGPKKNMW5RFP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Amortized Inference Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Hung H. Bui, Mykel J. Kochenderfer, Rui Shu, Shengjia Zhao, Stefano Ermon","submitted_at":"2018-05-23T00:14:56Z","abstract_excerpt":"The variational autoencoder (VAE) is a popular model for density estimation and representation learning. Canonically, the variational principle suggests to prefer an expressive inference model so that the variational approximation is accurate. However, it is often overlooked that an overly-expressive inference model can be detrimental to the test set performance of both the amortized posterior approximator and, more importantly, the generative density estimator. In this paper, we leverage the fact that VAEs rely on amortized inference and propose techniques for amortized inference regularizati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08913","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:56:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LPcfcH7tLEfehBhR8jcN9WPPgzDUvqPo3RKuDp073gtySMakDiFdC4Vl86DjeG/q5eeEZkV6I/5vwRj+Ikr+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T21:29:34.841115Z"},"content_sha256":"f6c81164fa36d1af4c1a3ab704da90562a4435fe1ff908d8d1096d562079fac3","schema_version":"1.0","event_id":"sha256:f6c81164fa36d1af4c1a3ab704da90562a4435fe1ff908d8d1096d562079fac3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5UGE2K3MMEPW7XOGPKKNMW5RFP/bundle.json","state_url":"https://pith.science/pith/5UGE2K3MMEPW7XOGPKKNMW5RFP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5UGE2K3MMEPW7XOGPKKNMW5RFP/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":"2026-06-03T21:29:34Z","links":{"resolver":"https://pith.science/pith/5UGE2K3MMEPW7XOGPKKNMW5RFP","bundle":"https://pith.science/pith/5UGE2K3MMEPW7XOGPKKNMW5RFP/bundle.json","state":"https://pith.science/pith/5UGE2K3MMEPW7XOGPKKNMW5RFP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5UGE2K3MMEPW7XOGPKKNMW5RFP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5UGE2K3MMEPW7XOGPKKNMW5RFP","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":"aa106c1b900c5c1636691aac8ceac88438703a386a0efa549d16d74fd668889c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-23T00:14:56Z","title_canon_sha256":"a41b85040ffc790922dc71a1555f8bdb67677fdb2143f11ed2ce79c2b1a52a6c"},"schema_version":"1.0","source":{"id":"1805.08913","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08913","created_at":"2026-05-17T23:56:41Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08913v2","created_at":"2026-05-17T23:56:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08913","created_at":"2026-05-17T23:56:41Z"},{"alias_kind":"pith_short_12","alias_value":"5UGE2K3MMEPW","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5UGE2K3MMEPW7XOG","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5UGE2K3M","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:f6c81164fa36d1af4c1a3ab704da90562a4435fe1ff908d8d1096d562079fac3","target":"graph","created_at":"2026-05-17T23:56:41Z","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 variational autoencoder (VAE) is a popular model for density estimation and representation learning. Canonically, the variational principle suggests to prefer an expressive inference model so that the variational approximation is accurate. However, it is often overlooked that an overly-expressive inference model can be detrimental to the test set performance of both the amortized posterior approximator and, more importantly, the generative density estimator. In this paper, we leverage the fact that VAEs rely on amortized inference and propose techniques for amortized inference regularizati","authors_text":"Hung H. Bui, Mykel J. Kochenderfer, Rui Shu, Shengjia Zhao, Stefano Ermon","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-23T00:14:56Z","title":"Amortized Inference Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08913","kind":"arxiv","version":2},"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:aeef5d51add2b36ebd8dec400196423b26111f587d931ee233d4b1b0234250dd","target":"record","created_at":"2026-05-17T23:56:41Z","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":"aa106c1b900c5c1636691aac8ceac88438703a386a0efa549d16d74fd668889c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-23T00:14:56Z","title_canon_sha256":"a41b85040ffc790922dc71a1555f8bdb67677fdb2143f11ed2ce79c2b1a52a6c"},"schema_version":"1.0","source":{"id":"1805.08913","kind":"arxiv","version":2}},"canonical_sha256":"ed0c4d2b6c611f6fddc67a94d65bb12bf9654c9796a6442a48898389c12cb46d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed0c4d2b6c611f6fddc67a94d65bb12bf9654c9796a6442a48898389c12cb46d","first_computed_at":"2026-05-17T23:56:41.330002Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:41.330002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rrdM7ISYgAva8nQm3Nd+ovIJ0tY78v5StaOdAmkPOHcNcATPeky+QxtdVe5KOCXl+Q5F1qAukreUa58VbmEECA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:41.330613Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.08913","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aeef5d51add2b36ebd8dec400196423b26111f587d931ee233d4b1b0234250dd","sha256:f6c81164fa36d1af4c1a3ab704da90562a4435fe1ff908d8d1096d562079fac3"],"state_sha256":"d8cbacfb1cec2d582a09682d1ed510cffdb0ea8c36cb4660832b498767db5bf6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n+NH/j+LAEjcHAWx71KeUbBJywwhybW3EygQgxqA0Eqqo5HIz6PKNmjen6ephQhy/PUAu7Tsjl1MxtvFnwDdCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T21:29:34.843201Z","bundle_sha256":"a111ab191ffcf5b389e4ec91c3845b02a9f94097fc5969f9dc5387e6cb6824ce"}}