{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZCFW6MOJYVGFRXI2X4UXIKMC24","short_pith_number":"pith:ZCFW6MOJ","schema_version":"1.0","canonical_sha256":"c88b6f31c9c54c58dd1abf29742982d704b55a81493fbe0a996ee14855b8c5c1","source":{"kind":"arxiv","id":"2107.00630","version":6},"attestation_state":"computed","paper":{"title":"Variational Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ben Poole, Diederik P. Kingma, Jonathan Ho, Tim Salimans","submitted_at":"2021-07-01T17:43:20Z","abstract_excerpt":"Diffusion-based generative models have demonstrated a capacity for perceptually impressive synthesis, but can they also be great likelihood-based models? We answer this in the affirmative, and introduce a family of diffusion-based generative models that obtain state-of-the-art likelihoods on standard image density estimation benchmarks. Unlike other diffusion-based models, our method allows for efficient optimization of the noise schedule jointly with the rest of the model. We show that the variational lower bound (VLB) simplifies to a remarkably short expression in terms of the signal-to-nois"},"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":"2107.00630","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-01T17:43:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"950a3c49b5783bcdd28775c8a4177d7bc28ebea5273bca897bd013ac7905fd3e","abstract_canon_sha256":"df8970d4ec95a5a419a230803ded73678c2a20cd5157fdfe5b6fbbb3705b2d67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:00:54.452986Z","signature_b64":"KlrWgOP79ZT4L2JFSP1uYPYOF7rEhhmWrC5GMD7M/FMjoVQq2m89Xcu2oats33F4tSmRvOXKj5YyQDZoKJt+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c88b6f31c9c54c58dd1abf29742982d704b55a81493fbe0a996ee14855b8c5c1","last_reissued_at":"2026-07-05T06:00:54.452563Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:00:54.452563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ben Poole, Diederik P. Kingma, Jonathan Ho, Tim Salimans","submitted_at":"2021-07-01T17:43:20Z","abstract_excerpt":"Diffusion-based generative models have demonstrated a capacity for perceptually impressive synthesis, but can they also be great likelihood-based models? We answer this in the affirmative, and introduce a family of diffusion-based generative models that obtain state-of-the-art likelihoods on standard image density estimation benchmarks. Unlike other diffusion-based models, our method allows for efficient optimization of the noise schedule jointly with the rest of the model. We show that the variational lower bound (VLB) simplifies to a remarkably short expression in terms of the signal-to-nois"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.00630","kind":"arxiv","version":6},"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/2107.00630/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":"2107.00630","created_at":"2026-07-05T06:00:54.452627+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.00630v6","created_at":"2026-07-05T06:00:54.452627+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.00630","created_at":"2026-07-05T06:00:54.452627+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZCFW6MOJYVGF","created_at":"2026-07-05T06:00:54.452627+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZCFW6MOJYVGFRXI2","created_at":"2026-07-05T06:00:54.452627+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZCFW6MOJ","created_at":"2026-07-05T06:00:54.452627+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31576","citing_title":"Introduction to Stochastic Differential Equations for Generative Machine Learning: A Variational Perspective","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10023","citing_title":"Learning the Universe: Posterior Reliability of Neural Generative Models in High-Dimensional Field-Level Inference of Cosmic Initial Conditions","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21489","citing_title":"Variance Reduction for Expectations with Diffusion Teachers","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2401.00436","citing_title":"Diff-PCR: Diffusion-Based Correspondence Searching in Doubly Stochastic Matrix Space for Point Cloud Registration","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2409.08248","citing_title":"TextBoost: Boosting Text Encoder for Personalized Text-to-Image Generation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2503.14333","citing_title":"Characterizing higher-order representations through generative diffusion models explains human decoded neurofeedback performance","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22338","citing_title":"Physics-Informed Generative Solver: Bridging Data-Driven Priors and Conservation Laws for Stable Spatiotemporal Field Reconstruction","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21489","citing_title":"Variance Reduction for Expectations with Diffusion Teachers","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17693","citing_title":"Fine-tuning Pocket-Aware Diffusion Models via Denoising Policy Optimization","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2603.10093","citing_title":"Equivariant Asynchronous Diffusion: An Adaptive Denoising Schedule for Accelerated Molecular Conformation Generation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2204.03458","citing_title":"Video Diffusion Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2209.14687","citing_title":"Diffusion Posterior Sampling for General Noisy Inverse Problems","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2205.11487","citing_title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2112.10752","citing_title":"High-Resolution Image Synthesis with Latent Diffusion Models","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23536","citing_title":"$Z^2$-Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2202.00512","citing_title":"Progressive Distillation for Fast Sampling of Diffusion Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06829","citing_title":"A Unified Measure-Theoretic View of Diffusion, Score-Based, and Flow Matching Generative Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07100","citing_title":"TRACE: Transport Alignment Conformal Prediction via Diffusion and Flow Matching Models","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2210.02303","citing_title":"Imagen Video: High Definition Video Generation with Diffusion Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2207.12598","citing_title":"Classifier-Free Diffusion Guidance","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15938","citing_title":"VADF: Vision-Adaptive Diffusion Policy Framework for Efficient Robotic Manipulation","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZCFW6MOJYVGFRXI2X4UXIKMC24","json":"https://pith.science/pith/ZCFW6MOJYVGFRXI2X4UXIKMC24.json","graph_json":"https://pith.science/api/pith-number/ZCFW6MOJYVGFRXI2X4UXIKMC24/graph.json","events_json":"https://pith.science/api/pith-number/ZCFW6MOJYVGFRXI2X4UXIKMC24/events.json","paper":"https://pith.science/paper/ZCFW6MOJ"},"agent_actions":{"view_html":"https://pith.science/pith/ZCFW6MOJYVGFRXI2X4UXIKMC24","download_json":"https://pith.science/pith/ZCFW6MOJYVGFRXI2X4UXIKMC24.json","view_paper":"https://pith.science/paper/ZCFW6MOJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.00630&json=true","fetch_graph":"https://pith.science/api/pith-number/ZCFW6MOJYVGFRXI2X4UXIKMC24/graph.json","fetch_events":"https://pith.science/api/pith-number/ZCFW6MOJYVGFRXI2X4UXIKMC24/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZCFW6MOJYVGFRXI2X4UXIKMC24/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZCFW6MOJYVGFRXI2X4UXIKMC24/action/storage_attestation","attest_author":"https://pith.science/pith/ZCFW6MOJYVGFRXI2X4UXIKMC24/action/author_attestation","sign_citation":"https://pith.science/pith/ZCFW6MOJYVGFRXI2X4UXIKMC24/action/citation_signature","submit_replication":"https://pith.science/pith/ZCFW6MOJYVGFRXI2X4UXIKMC24/action/replication_record"}},"created_at":"2026-07-05T06:00:54.452627+00:00","updated_at":"2026-07-05T06:00:54.452627+00:00"}