{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:GKDJDK53WMHA23PNAKPRDXQD3T","short_pith_number":"pith:GKDJDK53","canonical_record":{"source":{"id":"1907.08956","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-21T11:09:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bfe58b698897576904cabc3bbd516023ab0abf44c15304c907837133846b4563","abstract_canon_sha256":"044fd6b0635c5e1d5c55229478decb6171aded18cb67c3ee359e44f939320a36"},"schema_version":"1.0"},"canonical_sha256":"328691abbbb30e0d6ded029f11de03dce5f1bb204456dd8220928f3a19871137","source":{"kind":"arxiv","id":"1907.08956","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.08956","created_at":"2026-05-17T23:40:02Z"},{"alias_kind":"arxiv_version","alias_value":"1907.08956v1","created_at":"2026-05-17T23:40:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.08956","created_at":"2026-05-17T23:40:02Z"},{"alias_kind":"pith_short_12","alias_value":"GKDJDK53WMHA","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"GKDJDK53WMHA23PN","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"GKDJDK53","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:GKDJDK53WMHA23PNAKPRDXQD3T","target":"record","payload":{"canonical_record":{"source":{"id":"1907.08956","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-21T11:09:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bfe58b698897576904cabc3bbd516023ab0abf44c15304c907837133846b4563","abstract_canon_sha256":"044fd6b0635c5e1d5c55229478decb6171aded18cb67c3ee359e44f939320a36"},"schema_version":"1.0"},"canonical_sha256":"328691abbbb30e0d6ded029f11de03dce5f1bb204456dd8220928f3a19871137","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:02.600595Z","signature_b64":"ZvoFXJQqBX4/13sDYTl2WjflqyfURGEKyGAO4iCel8ccYLuZHGcCQvviC9ebK4IsINX6C5Efv1VrMhhE/DulAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"328691abbbb30e0d6ded029f11de03dce5f1bb204456dd8220928f3a19871137","last_reissued_at":"2026-05-17T23:40:02.599941Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:02.599941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.08956","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":"2026-05-17T23:40:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DM8n7eXVKknPkkeJQts/o8qeFLazSdPGzcZ0ZBjNU5h0VdiMXLuUcIc0OOds5DbLDRCoQc1YlFqVmuHY7gPODQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T11:25:56.280027Z"},"content_sha256":"e129f6a753604bb6e9b692f84cdbd66d404e6785b86dedab2a6dfd19b9310dac","schema_version":"1.0","event_id":"sha256:e129f6a753604bb6e9b692f84cdbd66d404e6785b86dedab2a6dfd19b9310dac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:GKDJDK53WMHA23PNAKPRDXQD3T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tutorial: Deriving the Standard Variational Autoencoder (VAE) Loss Function","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Stephen Odaibo","submitted_at":"2019-07-21T11:09:42Z","abstract_excerpt":"In Bayesian machine learning, the posterior distribution is typically computationally intractable, hence variational inference is often required. In this approach, an evidence lower bound on the log likelihood of data is maximized during training. Variational Autoencoders (VAE) are one important example where variational inference is utilized. In this tutorial, we derive the variational lower bound loss function of the standard variational autoencoder. We do so in the instance of a gaussian latent prior and gaussian approximate posterior, under which assumptions the Kullback-Leibler term in th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.08956","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":"2026-05-17T23:40:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"he/gdzhmCMo2UfN4Lk0S1nTdMx8rT5S8kO1ptVMa1U+IiixOOgXL5GXCn61MjXNy3ndSWI2RJ16HELuzkedMBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T11:25:56.280768Z"},"content_sha256":"36fabb6452b325e06d843b023276ac531de7cadc17b13bdb60437f29056c9ab6","schema_version":"1.0","event_id":"sha256:36fabb6452b325e06d843b023276ac531de7cadc17b13bdb60437f29056c9ab6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GKDJDK53WMHA23PNAKPRDXQD3T/bundle.json","state_url":"https://pith.science/pith/GKDJDK53WMHA23PNAKPRDXQD3T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GKDJDK53WMHA23PNAKPRDXQD3T/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":"2026-06-09T11:25:56Z","links":{"resolver":"https://pith.science/pith/GKDJDK53WMHA23PNAKPRDXQD3T","bundle":"https://pith.science/pith/GKDJDK53WMHA23PNAKPRDXQD3T/bundle.json","state":"https://pith.science/pith/GKDJDK53WMHA23PNAKPRDXQD3T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GKDJDK53WMHA23PNAKPRDXQD3T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:GKDJDK53WMHA23PNAKPRDXQD3T","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":"044fd6b0635c5e1d5c55229478decb6171aded18cb67c3ee359e44f939320a36","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-21T11:09:42Z","title_canon_sha256":"bfe58b698897576904cabc3bbd516023ab0abf44c15304c907837133846b4563"},"schema_version":"1.0","source":{"id":"1907.08956","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.08956","created_at":"2026-05-17T23:40:02Z"},{"alias_kind":"arxiv_version","alias_value":"1907.08956v1","created_at":"2026-05-17T23:40:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.08956","created_at":"2026-05-17T23:40:02Z"},{"alias_kind":"pith_short_12","alias_value":"GKDJDK53WMHA","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"GKDJDK53WMHA23PN","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"GKDJDK53","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:36fabb6452b325e06d843b023276ac531de7cadc17b13bdb60437f29056c9ab6","target":"graph","created_at":"2026-05-17T23:40:02Z","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":"In Bayesian machine learning, the posterior distribution is typically computationally intractable, hence variational inference is often required. In this approach, an evidence lower bound on the log likelihood of data is maximized during training. Variational Autoencoders (VAE) are one important example where variational inference is utilized. In this tutorial, we derive the variational lower bound loss function of the standard variational autoencoder. We do so in the instance of a gaussian latent prior and gaussian approximate posterior, under which assumptions the Kullback-Leibler term in th","authors_text":"Stephen Odaibo","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-21T11:09:42Z","title":"Tutorial: Deriving the Standard Variational Autoencoder (VAE) Loss Function"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.08956","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:e129f6a753604bb6e9b692f84cdbd66d404e6785b86dedab2a6dfd19b9310dac","target":"record","created_at":"2026-05-17T23:40:02Z","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":"044fd6b0635c5e1d5c55229478decb6171aded18cb67c3ee359e44f939320a36","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-21T11:09:42Z","title_canon_sha256":"bfe58b698897576904cabc3bbd516023ab0abf44c15304c907837133846b4563"},"schema_version":"1.0","source":{"id":"1907.08956","kind":"arxiv","version":1}},"canonical_sha256":"328691abbbb30e0d6ded029f11de03dce5f1bb204456dd8220928f3a19871137","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"328691abbbb30e0d6ded029f11de03dce5f1bb204456dd8220928f3a19871137","first_computed_at":"2026-05-17T23:40:02.599941Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:02.599941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZvoFXJQqBX4/13sDYTl2WjflqyfURGEKyGAO4iCel8ccYLuZHGcCQvviC9ebK4IsINX6C5Efv1VrMhhE/DulAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:02.600595Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.08956","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e129f6a753604bb6e9b692f84cdbd66d404e6785b86dedab2a6dfd19b9310dac","sha256:36fabb6452b325e06d843b023276ac531de7cadc17b13bdb60437f29056c9ab6"],"state_sha256":"9da61d3dd0f589507761c273358c66aefbd65cc91020b59a905339ebe19d52af"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mHCQ4xo0HK70gbxU/sqQEX7xWsldTHhCRMPxBZ/5zL8NI8kU/bx0AAWGS7y4fqRmQDsAXEDoUB1QLml9DPbrDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T11:25:56.284755Z","bundle_sha256":"661fc67de3322e90ed72056b3fdb8b3fde26041a6bf212e25dcb28e1d91aea7d"}}