{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TYK473L6DSYUFCPDJ2SRADDHTZ","short_pith_number":"pith:TYK473L6","schema_version":"1.0","canonical_sha256":"9e15cfed7e1cb14289e34ea5100c679e5f6ce2c07514ef7336ab159f35271371","source":{"kind":"arxiv","id":"2007.03898","version":3},"attestation_state":"computed","paper":{"title":"NVAE: A Deep Hierarchical Variational Autoencoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Arash Vahdat, Jan Kautz","submitted_at":"2020-07-08T04:56:56Z","abstract_excerpt":"Normalizing flows, autoregressive models, variational autoencoders (VAEs), and deep energy-based models are among competing likelihood-based frameworks for deep generative learning. Among them, VAEs have the advantage of fast and tractable sampling and easy-to-access encoding networks. However, they are currently outperformed by other models such as normalizing flows and autoregressive models. While the majority of the research in VAEs is focused on the statistical challenges, we explore the orthogonal direction of carefully designing neural architectures for hierarchical VAEs. We propose Nouv"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2007.03898","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-07-08T04:56:56Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"e0bb17826ce91fdccc70d31794704a4e8321de2591ee2cdf806f0621567a10c4","abstract_canon_sha256":"9927584ad749d5dc6d037199030cbec6bfe42d456701a32ed6564cee424039d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:05:26.239750Z","signature_b64":"3+z0d+vsuNNZ/2X6kMDt7LIlyAtyUdHNBAb6rM5iquiYHS8v2R4MR3dK667LJA0dWunjREesnQPvNOX8Z2V1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e15cfed7e1cb14289e34ea5100c679e5f6ce2c07514ef7336ab159f35271371","last_reissued_at":"2026-07-05T02:05:26.239311Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:05:26.239311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NVAE: A Deep Hierarchical Variational Autoencoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Arash Vahdat, Jan Kautz","submitted_at":"2020-07-08T04:56:56Z","abstract_excerpt":"Normalizing flows, autoregressive models, variational autoencoders (VAEs), and deep energy-based models are among competing likelihood-based frameworks for deep generative learning. Among them, VAEs have the advantage of fast and tractable sampling and easy-to-access encoding networks. However, they are currently outperformed by other models such as normalizing flows and autoregressive models. While the majority of the research in VAEs is focused on the statistical challenges, we explore the orthogonal direction of carefully designing neural architectures for hierarchical VAEs. We propose Nouv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03898","kind":"arxiv","version":3},"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/2007.03898/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2007.03898","created_at":"2026-07-05T02:05:26.239377+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.03898v3","created_at":"2026-07-05T02:05:26.239377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03898","created_at":"2026-07-05T02:05:26.239377+00:00"},{"alias_kind":"pith_short_12","alias_value":"TYK473L6DSYU","created_at":"2026-07-05T02:05:26.239377+00:00"},{"alias_kind":"pith_short_16","alias_value":"TYK473L6DSYUFCPD","created_at":"2026-07-05T02:05:26.239377+00:00"},{"alias_kind":"pith_short_8","alias_value":"TYK473L6","created_at":"2026-07-05T02:05:26.239377+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01275","citing_title":"eXact-Prior Variational Autoencoder (X-VAE): Learning Data-Adaptive Gaussian Mixture Priors for Latent Distributions","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2101.02388","citing_title":"Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2102.09672","citing_title":"Improved Denoising Diffusion Probabilistic Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02438","citing_title":"Mitigating Data Scarcity in Spaceflight Applications for Offline Reinforcement Learning Using Physics-Informed Deep Generative Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2104.10157","citing_title":"VideoGPT: Video Generation using VQ-VAE and Transformers","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2105.05233","citing_title":"Diffusion Models Beat GANs on Image Synthesis","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03413","citing_title":"Learning to Theorize the World from Observation","ref_index":141,"is_internal_anchor":false},{"citing_arxiv_id":"2204.06125","citing_title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TYK473L6DSYUFCPDJ2SRADDHTZ","json":"https://pith.science/pith/TYK473L6DSYUFCPDJ2SRADDHTZ.json","graph_json":"https://pith.science/api/pith-number/TYK473L6DSYUFCPDJ2SRADDHTZ/graph.json","events_json":"https://pith.science/api/pith-number/TYK473L6DSYUFCPDJ2SRADDHTZ/events.json","paper":"https://pith.science/paper/TYK473L6"},"agent_actions":{"view_html":"https://pith.science/pith/TYK473L6DSYUFCPDJ2SRADDHTZ","download_json":"https://pith.science/pith/TYK473L6DSYUFCPDJ2SRADDHTZ.json","view_paper":"https://pith.science/paper/TYK473L6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.03898&json=true","fetch_graph":"https://pith.science/api/pith-number/TYK473L6DSYUFCPDJ2SRADDHTZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TYK473L6DSYUFCPDJ2SRADDHTZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TYK473L6DSYUFCPDJ2SRADDHTZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TYK473L6DSYUFCPDJ2SRADDHTZ/action/storage_attestation","attest_author":"https://pith.science/pith/TYK473L6DSYUFCPDJ2SRADDHTZ/action/author_attestation","sign_citation":"https://pith.science/pith/TYK473L6DSYUFCPDJ2SRADDHTZ/action/citation_signature","submit_replication":"https://pith.science/pith/TYK473L6DSYUFCPDJ2SRADDHTZ/action/replication_record"}},"created_at":"2026-07-05T02:05:26.239377+00:00","updated_at":"2026-07-05T02:05:26.239377+00:00"}