{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GCSQLLNLAQEFXTJO6C2C7QLUHD","short_pith_number":"pith:GCSQLLNL","canonical_record":{"source":{"id":"2412.01373","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-02T10:58:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d70027084bf07f7de46b82f43ff17aa11e085f11ef348e83ffe8a26c7d2452f2","abstract_canon_sha256":"8035fd872e192cac16e461a37b07f945ebf59c1d64809d9e975ada9a7273c749"},"schema_version":"1.0"},"canonical_sha256":"30a505adab04085bcd2ef0b42fc17438f4b32c5a40af87ab47681d754cd54d45","source":{"kind":"arxiv","id":"2412.01373","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01373","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01373v1","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01373","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"pith_short_12","alias_value":"GCSQLLNLAQEF","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"pith_short_16","alias_value":"GCSQLLNLAQEFXTJO","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"pith_short_8","alias_value":"GCSQLLNL","created_at":"2026-07-05T09:42:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GCSQLLNLAQEFXTJO6C2C7QLUHD","target":"record","payload":{"canonical_record":{"source":{"id":"2412.01373","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-02T10:58:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d70027084bf07f7de46b82f43ff17aa11e085f11ef348e83ffe8a26c7d2452f2","abstract_canon_sha256":"8035fd872e192cac16e461a37b07f945ebf59c1d64809d9e975ada9a7273c749"},"schema_version":"1.0"},"canonical_sha256":"30a505adab04085bcd2ef0b42fc17438f4b32c5a40af87ab47681d754cd54d45","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:58.996882Z","signature_b64":"dFMaayhZPCXMy7Nd1sldh50bWkA/zKaUTcS/jHtX9qNgjXb973VnLlQzRz1/tHXPl4YKv1Ywsda399aAxnp1Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30a505adab04085bcd2ef0b42fc17438f4b32c5a40af87ab47681d754cd54d45","last_reissued_at":"2026-07-05T09:42:58.996358Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:58.996358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.01373","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":"2026-07-05T09:42:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZFbj9t/QUomr0iEhLIj8Ut3Hqtsp8Mf+jQHODVYpu0qX97V9MIyIEPUqGd4RALEN7H0hG1fEbYsmTzQrgiHsDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:05:02.272123Z"},"content_sha256":"2e4c4dc7fb9a34663cf73088932feda7ae0330eff0ea95a234d36bf4527d6dc1","schema_version":"1.0","event_id":"sha256:2e4c4dc7fb9a34663cf73088932feda7ae0330eff0ea95a234d36bf4527d6dc1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GCSQLLNLAQEFXTJO6C2C7QLUHD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical VAE with a Diffusion-based VampPrior","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anna Kuzina, Jakub M. Tomczak","submitted_at":"2024-12-02T10:58:09Z","abstract_excerpt":"Deep hierarchical variational autoencoders (VAEs) are powerful latent variable generative models. In this paper, we introduce Hierarchical VAE with Diffusion-based Variational Mixture of the Posterior Prior (VampPrior). We apply amortization to scale the VampPrior to models with many stochastic layers. The proposed approach allows us to achieve better performance compared to the original VampPrior work and other deep hierarchical VAEs, while using fewer parameters. We empirically validate our method on standard benchmark datasets (MNIST, OMNIGLOT, CIFAR10) and demonstrate improved training sta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01373","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.01373/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T09:42:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KsmZPAOubQ3jvyQ/h52fokujsKAr7snkc5koUyyT8LFUy92e/yT9nup3DjIB6NVTHkrCnB1mWhJXbar0LInFBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:05:02.272760Z"},"content_sha256":"0a6e6b40e7ae278090fea9bd53716aea78197c14285a3432da6122b017bce7cd","schema_version":"1.0","event_id":"sha256:0a6e6b40e7ae278090fea9bd53716aea78197c14285a3432da6122b017bce7cd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GCSQLLNLAQEFXTJO6C2C7QLUHD/bundle.json","state_url":"https://pith.science/pith/GCSQLLNLAQEFXTJO6C2C7QLUHD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GCSQLLNLAQEFXTJO6C2C7QLUHD/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":"2026-08-08T09:05:02Z","links":{"resolver":"https://pith.science/pith/GCSQLLNLAQEFXTJO6C2C7QLUHD","bundle":"https://pith.science/pith/GCSQLLNLAQEFXTJO6C2C7QLUHD/bundle.json","state":"https://pith.science/pith/GCSQLLNLAQEFXTJO6C2C7QLUHD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GCSQLLNLAQEFXTJO6C2C7QLUHD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GCSQLLNLAQEFXTJO6C2C7QLUHD","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":"8035fd872e192cac16e461a37b07f945ebf59c1d64809d9e975ada9a7273c749","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-02T10:58:09Z","title_canon_sha256":"d70027084bf07f7de46b82f43ff17aa11e085f11ef348e83ffe8a26c7d2452f2"},"schema_version":"1.0","source":{"id":"2412.01373","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01373","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01373v1","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01373","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"pith_short_12","alias_value":"GCSQLLNLAQEF","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"pith_short_16","alias_value":"GCSQLLNLAQEFXTJO","created_at":"2026-07-05T09:42:58Z"},{"alias_kind":"pith_short_8","alias_value":"GCSQLLNL","created_at":"2026-07-05T09:42:58Z"}],"graph_snapshots":[{"event_id":"sha256:0a6e6b40e7ae278090fea9bd53716aea78197c14285a3432da6122b017bce7cd","target":"graph","created_at":"2026-07-05T09:42:58Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.01373/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep hierarchical variational autoencoders (VAEs) are powerful latent variable generative models. In this paper, we introduce Hierarchical VAE with Diffusion-based Variational Mixture of the Posterior Prior (VampPrior). We apply amortization to scale the VampPrior to models with many stochastic layers. The proposed approach allows us to achieve better performance compared to the original VampPrior work and other deep hierarchical VAEs, while using fewer parameters. We empirically validate our method on standard benchmark datasets (MNIST, OMNIGLOT, CIFAR10) and demonstrate improved training sta","authors_text":"Anna Kuzina, Jakub M. Tomczak","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-02T10:58:09Z","title":"Hierarchical VAE with a Diffusion-based VampPrior"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01373","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":"sha256:2e4c4dc7fb9a34663cf73088932feda7ae0330eff0ea95a234d36bf4527d6dc1","target":"record","created_at":"2026-07-05T09:42:58Z","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":"8035fd872e192cac16e461a37b07f945ebf59c1d64809d9e975ada9a7273c749","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-02T10:58:09Z","title_canon_sha256":"d70027084bf07f7de46b82f43ff17aa11e085f11ef348e83ffe8a26c7d2452f2"},"schema_version":"1.0","source":{"id":"2412.01373","kind":"arxiv","version":1}},"canonical_sha256":"30a505adab04085bcd2ef0b42fc17438f4b32c5a40af87ab47681d754cd54d45","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30a505adab04085bcd2ef0b42fc17438f4b32c5a40af87ab47681d754cd54d45","first_computed_at":"2026-07-05T09:42:58.996358Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:58.996358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dFMaayhZPCXMy7Nd1sldh50bWkA/zKaUTcS/jHtX9qNgjXb973VnLlQzRz1/tHXPl4YKv1Ywsda399aAxnp1Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:58.996882Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.01373","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e4c4dc7fb9a34663cf73088932feda7ae0330eff0ea95a234d36bf4527d6dc1","sha256:0a6e6b40e7ae278090fea9bd53716aea78197c14285a3432da6122b017bce7cd"],"state_sha256":"a1311e0dad3b4e053b963922508cea7d507175b784030cce13bda5db75cdb9fc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dUPaS5Lquv+RB8zXNoFB2ugV5mX2v6LgLfjUI9tSDmgeHqwlwudPwYd1NJX/SLVv5jPcWgEW4CeodHkIBatwCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:05:02.284122Z","bundle_sha256":"d1439b9c56fd2adc644cbeb77f4fbe8816537f2354b8e9232a10d8507e361e5a"}}