{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7RMNL76RC6PK6D36E2HQIWIV2K","short_pith_number":"pith:7RMNL76R","canonical_record":{"source":{"id":"1901.05534","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-16T21:32:33Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a3f546ea3477b65a02a295329df94838cf8401dbf6911cf265b8e0239fd245db","abstract_canon_sha256":"dd16ab481005f0cc7bc352a835c1f8c9e8f448f2788b8deadd156562f071e2df"},"schema_version":"1.0"},"canonical_sha256":"fc58d5ffd1179eaf0f7e268f045915d2bee0391add1e8872e0ba9a069956c4ff","source":{"kind":"arxiv","id":"1901.05534","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.05534","created_at":"2026-05-17T23:55:16Z"},{"alias_kind":"arxiv_version","alias_value":"1901.05534v2","created_at":"2026-05-17T23:55:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.05534","created_at":"2026-05-17T23:55:16Z"},{"alias_kind":"pith_short_12","alias_value":"7RMNL76RC6PK","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7RMNL76RC6PK6D36","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7RMNL76R","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7RMNL76RC6PK6D36E2HQIWIV2K","target":"record","payload":{"canonical_record":{"source":{"id":"1901.05534","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-16T21:32:33Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a3f546ea3477b65a02a295329df94838cf8401dbf6911cf265b8e0239fd245db","abstract_canon_sha256":"dd16ab481005f0cc7bc352a835c1f8c9e8f448f2788b8deadd156562f071e2df"},"schema_version":"1.0"},"canonical_sha256":"fc58d5ffd1179eaf0f7e268f045915d2bee0391add1e8872e0ba9a069956c4ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:16.818841Z","signature_b64":"x+NZZMe78FMplKrRRiHN8MmoPJPWi74rqYneF+KemLYwV2TmLhHT6ARvbWjabWLD35qzB2F6Ee8meIXBLMSIBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc58d5ffd1179eaf0f7e268f045915d2bee0391add1e8872e0ba9a069956c4ff","last_reissued_at":"2026-05-17T23:55:16.818231Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:16.818231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.05534","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":"2026-05-17T23:55:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w9D+Wd5iDf6Z+PnnROzggnituLMixJBbYThs8QZLJ6NMybATY42n+pu5jyUqpefSeew43J/6r50ayJW05n6pBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T12:20:28.062929Z"},"content_sha256":"d18f78d27a278d0cda108e2af21a289477291e42d422e4c4f1c18f5c35620405","schema_version":"1.0","event_id":"sha256:d18f78d27a278d0cda108e2af21a289477291e42d422e4c4f1c18f5c35620405"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7RMNL76RC6PK6D36E2HQIWIV2K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lagging Inference Networks and Posterior Collapse in Variational Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Spokoyny, Graham Neubig, Junxian He, Taylor Berg-Kirkpatrick","submitted_at":"2019-01-16T21:32:33Z","abstract_excerpt":"The variational autoencoder (VAE) is a popular combination of deep latent variable model and accompanying variational learning technique. By using a neural inference network to approximate the model's posterior on latent variables, VAEs efficiently parameterize a lower bound on marginal data likelihood that can be optimized directly via gradient methods. In practice, however, VAE training often results in a degenerate local optimum known as \"posterior collapse\" where the model learns to ignore the latent variable and the approximate posterior mimics the prior. In this paper, we investigate pos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.05534","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":"2026-05-17T23:55:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5GekFzmKnbCegkKKbexMtJy4FPDzqda9ZSMQVepgys5Iovb7ooqbSeEcRoZeLyP8KkDp1sofdNaTno2oHenKDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T12:20:28.063377Z"},"content_sha256":"dcff270b120d5ed2487c389453db61eb605c27b480220d8462796c35a2b7538f","schema_version":"1.0","event_id":"sha256:dcff270b120d5ed2487c389453db61eb605c27b480220d8462796c35a2b7538f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7RMNL76RC6PK6D36E2HQIWIV2K/bundle.json","state_url":"https://pith.science/pith/7RMNL76RC6PK6D36E2HQIWIV2K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7RMNL76RC6PK6D36E2HQIWIV2K/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":"2026-06-03T12:20:28Z","links":{"resolver":"https://pith.science/pith/7RMNL76RC6PK6D36E2HQIWIV2K","bundle":"https://pith.science/pith/7RMNL76RC6PK6D36E2HQIWIV2K/bundle.json","state":"https://pith.science/pith/7RMNL76RC6PK6D36E2HQIWIV2K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7RMNL76RC6PK6D36E2HQIWIV2K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7RMNL76RC6PK6D36E2HQIWIV2K","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":"dd16ab481005f0cc7bc352a835c1f8c9e8f448f2788b8deadd156562f071e2df","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-16T21:32:33Z","title_canon_sha256":"a3f546ea3477b65a02a295329df94838cf8401dbf6911cf265b8e0239fd245db"},"schema_version":"1.0","source":{"id":"1901.05534","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.05534","created_at":"2026-05-17T23:55:16Z"},{"alias_kind":"arxiv_version","alias_value":"1901.05534v2","created_at":"2026-05-17T23:55:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.05534","created_at":"2026-05-17T23:55:16Z"},{"alias_kind":"pith_short_12","alias_value":"7RMNL76RC6PK","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7RMNL76RC6PK6D36","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7RMNL76R","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:dcff270b120d5ed2487c389453db61eb605c27b480220d8462796c35a2b7538f","target":"graph","created_at":"2026-05-17T23:55:16Z","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 combination of deep latent variable model and accompanying variational learning technique. By using a neural inference network to approximate the model's posterior on latent variables, VAEs efficiently parameterize a lower bound on marginal data likelihood that can be optimized directly via gradient methods. In practice, however, VAE training often results in a degenerate local optimum known as \"posterior collapse\" where the model learns to ignore the latent variable and the approximate posterior mimics the prior. In this paper, we investigate pos","authors_text":"Daniel Spokoyny, Graham Neubig, Junxian He, Taylor Berg-Kirkpatrick","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-16T21:32:33Z","title":"Lagging Inference Networks and Posterior Collapse in Variational Autoencoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.05534","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:d18f78d27a278d0cda108e2af21a289477291e42d422e4c4f1c18f5c35620405","target":"record","created_at":"2026-05-17T23:55:16Z","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":"dd16ab481005f0cc7bc352a835c1f8c9e8f448f2788b8deadd156562f071e2df","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-16T21:32:33Z","title_canon_sha256":"a3f546ea3477b65a02a295329df94838cf8401dbf6911cf265b8e0239fd245db"},"schema_version":"1.0","source":{"id":"1901.05534","kind":"arxiv","version":2}},"canonical_sha256":"fc58d5ffd1179eaf0f7e268f045915d2bee0391add1e8872e0ba9a069956c4ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc58d5ffd1179eaf0f7e268f045915d2bee0391add1e8872e0ba9a069956c4ff","first_computed_at":"2026-05-17T23:55:16.818231Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:16.818231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x+NZZMe78FMplKrRRiHN8MmoPJPWi74rqYneF+KemLYwV2TmLhHT6ARvbWjabWLD35qzB2F6Ee8meIXBLMSIBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:16.818841Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.05534","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d18f78d27a278d0cda108e2af21a289477291e42d422e4c4f1c18f5c35620405","sha256:dcff270b120d5ed2487c389453db61eb605c27b480220d8462796c35a2b7538f"],"state_sha256":"e9d60c5637ad1553dc0f3893880b676e37ce65efad92aeb0a1da6ba825c14149"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9ye2yTwhsAbeIS1cbRRTXTKESoikWSKComBVHE/AAvqX8+IA3z8UVlKY17hHe2FMN5XZBwTsE0Fzq7I6NsafAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T12:20:28.065391Z","bundle_sha256":"1e19cbdac9d8af969e31f4f87ac1ea8b69c8343d44151075b9377fd2bdf6d270"}}