{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:IEZIY6SPBQA7GSMQLIVIXGTI6P","short_pith_number":"pith:IEZIY6SP","canonical_record":{"source":{"id":"1807.04863","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-12T23:37:27Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"5fa5e21e89b940bc3cb88ae16f51620163abc2cad81a71e3f3f0bec462a8f483","abstract_canon_sha256":"a9b018e9c2e9ece15fc70ae30e527c4406cf92e6d4615fb75cc71f57afd6b57c"},"schema_version":"1.0"},"canonical_sha256":"41328c7a4f0c01f349905a2a8b9a68f3c8127f5995b62edbd77097222d75a621","source":{"kind":"arxiv","id":"1807.04863","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.04863","created_at":"2026-05-17T23:55:03Z"},{"alias_kind":"arxiv_version","alias_value":"1807.04863v2","created_at":"2026-05-17T23:55:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.04863","created_at":"2026-05-17T23:55:03Z"},{"alias_kind":"pith_short_12","alias_value":"IEZIY6SPBQA7","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"IEZIY6SPBQA7GSMQ","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"IEZIY6SP","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:IEZIY6SPBQA7GSMQLIVIXGTI6P","target":"record","payload":{"canonical_record":{"source":{"id":"1807.04863","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-12T23:37:27Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"5fa5e21e89b940bc3cb88ae16f51620163abc2cad81a71e3f3f0bec462a8f483","abstract_canon_sha256":"a9b018e9c2e9ece15fc70ae30e527c4406cf92e6d4615fb75cc71f57afd6b57c"},"schema_version":"1.0"},"canonical_sha256":"41328c7a4f0c01f349905a2a8b9a68f3c8127f5995b62edbd77097222d75a621","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:03.432686Z","signature_b64":"J5dxk0vpCzRIW+QOkc/4K+RsFZiFW8NwWyRKgQQJZ7jr9f+30zVB7gDR235psrEx9F/cXVFxUmv6pin+qMbQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41328c7a4f0c01f349905a2a8b9a68f3c8127f5995b62edbd77097222d75a621","last_reissued_at":"2026-05-17T23:55:03.432160Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:03.432160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.04863","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":"2026-05-17T23:55:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o++GGIeW17k428H/q9bseu4wPqu1iBhLXtbCdjhPMq+cN3m9KhC8xtY3NzDEy+ZI/LZSC0na0H2Sub5rxIW4Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T16:58:09.881330Z"},"content_sha256":"baa917b1d87e390b05150cdf061075f8f6d42e900a1440fdf2399e04d96c2384","schema_version":"1.0","event_id":"sha256:baa917b1d87e390b05150cdf061075f8f6d42e900a1440fdf2399e04d96c2384"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:IEZIY6SPBQA7GSMQLIVIXGTI6P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Avoiding Latent Variable Collapse With Generative Skip Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Adji B. Dieng, Alexander M. Rush, David M. Blei, Yoon Kim","submitted_at":"2018-07-12T23:37:27Z","abstract_excerpt":"Variational autoencoders learn distributions of high-dimensional data. They model data with a deep latent-variable model and then fit the model by maximizing a lower bound of the log marginal likelihood. VAEs can capture complex distributions, but they can also suffer from an issue known as \"latent variable collapse,\" especially if the likelihood model is powerful. Specifically, the lower bound involves an approximate posterior of the latent variables; this posterior \"collapses\" when it is set equal to the prior, i.e., when the approximate posterior is independent of the data. While VAEs learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.04863","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":"2026-05-17T23:55:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FMT9UM4n8ub2VmauaR1RbjqEB6DoOh30vuFIiKBI9ml0o3a4xJl8rQn0hfbOq16ZOaooP1vK1esTG6R6BKCXDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T16:58:09.881871Z"},"content_sha256":"83ff9997609189a08c995724dd6bfca24d84f3a8ce5095933c0dc33ca623ef60","schema_version":"1.0","event_id":"sha256:83ff9997609189a08c995724dd6bfca24d84f3a8ce5095933c0dc33ca623ef60"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IEZIY6SPBQA7GSMQLIVIXGTI6P/bundle.json","state_url":"https://pith.science/pith/IEZIY6SPBQA7GSMQLIVIXGTI6P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IEZIY6SPBQA7GSMQLIVIXGTI6P/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":"2026-06-01T16:58:09Z","links":{"resolver":"https://pith.science/pith/IEZIY6SPBQA7GSMQLIVIXGTI6P","bundle":"https://pith.science/pith/IEZIY6SPBQA7GSMQLIVIXGTI6P/bundle.json","state":"https://pith.science/pith/IEZIY6SPBQA7GSMQLIVIXGTI6P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IEZIY6SPBQA7GSMQLIVIXGTI6P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:IEZIY6SPBQA7GSMQLIVIXGTI6P","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":"a9b018e9c2e9ece15fc70ae30e527c4406cf92e6d4615fb75cc71f57afd6b57c","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-12T23:37:27Z","title_canon_sha256":"5fa5e21e89b940bc3cb88ae16f51620163abc2cad81a71e3f3f0bec462a8f483"},"schema_version":"1.0","source":{"id":"1807.04863","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.04863","created_at":"2026-05-17T23:55:03Z"},{"alias_kind":"arxiv_version","alias_value":"1807.04863v2","created_at":"2026-05-17T23:55:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.04863","created_at":"2026-05-17T23:55:03Z"},{"alias_kind":"pith_short_12","alias_value":"IEZIY6SPBQA7","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"IEZIY6SPBQA7GSMQ","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"IEZIY6SP","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:83ff9997609189a08c995724dd6bfca24d84f3a8ce5095933c0dc33ca623ef60","target":"graph","created_at":"2026-05-17T23:55:03Z","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":"Variational autoencoders learn distributions of high-dimensional data. They model data with a deep latent-variable model and then fit the model by maximizing a lower bound of the log marginal likelihood. VAEs can capture complex distributions, but they can also suffer from an issue known as \"latent variable collapse,\" especially if the likelihood model is powerful. Specifically, the lower bound involves an approximate posterior of the latent variables; this posterior \"collapses\" when it is set equal to the prior, i.e., when the approximate posterior is independent of the data. While VAEs learn","authors_text":"Adji B. Dieng, Alexander M. Rush, David M. Blei, Yoon Kim","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-12T23:37:27Z","title":"Avoiding Latent Variable Collapse With Generative Skip Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.04863","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:baa917b1d87e390b05150cdf061075f8f6d42e900a1440fdf2399e04d96c2384","target":"record","created_at":"2026-05-17T23:55:03Z","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":"a9b018e9c2e9ece15fc70ae30e527c4406cf92e6d4615fb75cc71f57afd6b57c","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-12T23:37:27Z","title_canon_sha256":"5fa5e21e89b940bc3cb88ae16f51620163abc2cad81a71e3f3f0bec462a8f483"},"schema_version":"1.0","source":{"id":"1807.04863","kind":"arxiv","version":2}},"canonical_sha256":"41328c7a4f0c01f349905a2a8b9a68f3c8127f5995b62edbd77097222d75a621","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41328c7a4f0c01f349905a2a8b9a68f3c8127f5995b62edbd77097222d75a621","first_computed_at":"2026-05-17T23:55:03.432160Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:03.432160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J5dxk0vpCzRIW+QOkc/4K+RsFZiFW8NwWyRKgQQJZ7jr9f+30zVB7gDR235psrEx9F/cXVFxUmv6pin+qMbQAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:03.432686Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.04863","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:baa917b1d87e390b05150cdf061075f8f6d42e900a1440fdf2399e04d96c2384","sha256:83ff9997609189a08c995724dd6bfca24d84f3a8ce5095933c0dc33ca623ef60"],"state_sha256":"835bbf8d2c68fbc75580c9f88e7664184b4bf157e31b66f9605f3929d955cf6b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P/uf/ZTqF0Jo43IfnmJ/n5PkvmIfC6gMJfhhWQUEw8MwtAop3KE5rTUdDJ6CtuPgM9s1zQFRTCgGquDteSKNCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T16:58:09.884535Z","bundle_sha256":"89c82cdf45211c3cbb4017ad938bff6a676a9aeacf8d6f3636548ffc258b2f84"}}