{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:73YHLPULVIHPYDIX3TENP46WVS","short_pith_number":"pith:73YHLPUL","schema_version":"1.0","canonical_sha256":"fef075be8baa0efc0d17dcc8d7f3d6ac947a77f5973757590c46ea527b8918c4","source":{"kind":"arxiv","id":"1906.00446","version":1},"attestation_state":"computed","paper":{"title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron van den Oord, Ali Razavi, Oriol Vinyals","submitted_at":"2019-06-02T16:46:42Z","abstract_excerpt":"We explore the use of Vector Quantized Variational AutoEncoder (VQ-VAE) models for large scale image generation. To this end, we scale and enhance the autoregressive priors used in VQ-VAE to generate synthetic samples of much higher coherence and fidelity than possible before. We use simple feed-forward encoder and decoder networks, making our model an attractive candidate for applications where the encoding and/or decoding speed is critical. Additionally, VQ-VAE requires sampling an autoregressive model only in the compressed latent space, which is an order of magnitude faster than sampling i"},"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":"1906.00446","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-02T16:46:42Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"0a49cd90e4c827c1ab7491b2f80a73635e861f71f42127011f4e2564d5abe161","abstract_canon_sha256":"349555727340ac237de7ba30642e7e922a9772aec02778adee3a76cbbb1bc96f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:27.033538Z","signature_b64":"G9AFkueEQb4RLP0aBHCTfWQokFgVywmCoxAiqkkPC/NvodtiV+UaObTJP9uIyVLYUueV9EcPlAxqV3cxCGaFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fef075be8baa0efc0d17dcc8d7f3d6ac947a77f5973757590c46ea527b8918c4","last_reissued_at":"2026-05-17T23:44:27.033027Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:27.033027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron van den Oord, Ali Razavi, Oriol Vinyals","submitted_at":"2019-06-02T16:46:42Z","abstract_excerpt":"We explore the use of Vector Quantized Variational AutoEncoder (VQ-VAE) models for large scale image generation. To this end, we scale and enhance the autoregressive priors used in VQ-VAE to generate synthetic samples of much higher coherence and fidelity than possible before. We use simple feed-forward encoder and decoder networks, making our model an attractive candidate for applications where the encoding and/or decoding speed is critical. Additionally, VQ-VAE requires sampling an autoregressive model only in the compressed latent space, which is an order of magnitude faster than sampling i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00446","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1906.00446","created_at":"2026-05-17T23:44:27.033117+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.00446v1","created_at":"2026-05-17T23:44:27.033117+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00446","created_at":"2026-05-17T23:44:27.033117+00:00"},{"alias_kind":"pith_short_12","alias_value":"73YHLPULVIHP","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"73YHLPULVIHPYDIX","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"73YHLPUL","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2505.24437","citing_title":"SwitchCodec: A High-Fidelity Nerual Audio Codec With Sparse Quantization","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2102.01293","citing_title":"Scaling Laws for Transfer","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2411.04983","citing_title":"DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2305.02463","citing_title":"Shap-E: Generating Conditional 3D Implicit Functions","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2309.16797","citing_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","ref_index":273,"is_internal_anchor":true},{"citing_arxiv_id":"2105.05233","citing_title":"Diffusion Models Beat GANs on Image Synthesis","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2205.11487","citing_title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09886","citing_title":"Network-Efficient World Model Token Streaming","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2112.00861","citing_title":"A General Language Assistant as a Laboratory for Alignment","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2112.10741","citing_title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07915","citing_title":"What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2204.06125","citing_title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2207.05221","citing_title":"Language Models (Mostly) Know What They Know","ref_index":126,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04366","citing_title":"Conditional Flow-VAE for Safety-Critical Traffic Scenario Generation","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/73YHLPULVIHPYDIX3TENP46WVS","json":"https://pith.science/pith/73YHLPULVIHPYDIX3TENP46WVS.json","graph_json":"https://pith.science/api/pith-number/73YHLPULVIHPYDIX3TENP46WVS/graph.json","events_json":"https://pith.science/api/pith-number/73YHLPULVIHPYDIX3TENP46WVS/events.json","paper":"https://pith.science/paper/73YHLPUL"},"agent_actions":{"view_html":"https://pith.science/pith/73YHLPULVIHPYDIX3TENP46WVS","download_json":"https://pith.science/pith/73YHLPULVIHPYDIX3TENP46WVS.json","view_paper":"https://pith.science/paper/73YHLPUL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.00446&json=true","fetch_graph":"https://pith.science/api/pith-number/73YHLPULVIHPYDIX3TENP46WVS/graph.json","fetch_events":"https://pith.science/api/pith-number/73YHLPULVIHPYDIX3TENP46WVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/73YHLPULVIHPYDIX3TENP46WVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/73YHLPULVIHPYDIX3TENP46WVS/action/storage_attestation","attest_author":"https://pith.science/pith/73YHLPULVIHPYDIX3TENP46WVS/action/author_attestation","sign_citation":"https://pith.science/pith/73YHLPULVIHPYDIX3TENP46WVS/action/citation_signature","submit_replication":"https://pith.science/pith/73YHLPULVIHPYDIX3TENP46WVS/action/replication_record"}},"created_at":"2026-05-17T23:44:27.033117+00:00","updated_at":"2026-05-17T23:44:27.033117+00:00"}