{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GGWSAIGBGVXMX4WGGWPUD4IG5Q","short_pith_number":"pith:GGWSAIGB","schema_version":"1.0","canonical_sha256":"31ad2020c1356ecbf2c6359f41f106ec3e6b985a5ee4f2c8ce30a67f3b5d4022","source":{"kind":"arxiv","id":"2102.09672","version":1},"attestation_state":"computed","paper":{"title":"Improved Denoising Diffusion Probabilistic Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Simple modifications let denoising diffusion models achieve competitive log-likelihoods while supporting much faster sampling.","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Nichol, Prafulla Dhariwal","submitted_at":"2021-02-18T23:44:17Z","abstract_excerpt":"Denoising diffusion probabilistic models (DDPM) are a class of generative models which have recently been shown to produce excellent samples. We show that with a few simple modifications, DDPMs can also achieve competitive log-likelihoods while maintaining high sample quality. Additionally, we find that learning variances of the reverse diffusion process allows sampling with an order of magnitude fewer forward passes with a negligible difference in sample quality, which is important for the practical deployment of these models. We additionally use precision and recall to compare how well DDPMs"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2102.09672","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-18T23:44:17Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4e2dc29951e3f3625c1d250081314238ec51d711b56de8887f75705726de5415","abstract_canon_sha256":"084e01d0615c400d02aaa5f09cea919e3d7f0df92b7095fff0a7e29e81394683"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:46.862127Z","signature_b64":"T3AiMkyfJlu2Y+Z6nuaJsKXIVnVE/X+ORci/yO4vMG4O5S3jkdTkw6CIC1qGY0aiMDEhdTzAqlGMv14SFIyrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31ad2020c1356ecbf2c6359f41f106ec3e6b985a5ee4f2c8ce30a67f3b5d4022","last_reissued_at":"2026-05-17T23:38:46.861530Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:46.861530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Denoising Diffusion Probabilistic Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Simple modifications let denoising diffusion models achieve competitive log-likelihoods while supporting much faster sampling.","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Nichol, Prafulla Dhariwal","submitted_at":"2021-02-18T23:44:17Z","abstract_excerpt":"Denoising diffusion probabilistic models (DDPM) are a class of generative models which have recently been shown to produce excellent samples. We show that with a few simple modifications, DDPMs can also achieve competitive log-likelihoods while maintaining high sample quality. Additionally, we find that learning variances of the reverse diffusion process allows sampling with an order of magnitude fewer forward passes with a negligible difference in sample quality, which is important for the practical deployment of these models. We additionally use precision and recall to compare how well DDPMs"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We show that with a few simple modifications, DDPMs can also achieve competitive log-likelihoods while maintaining high sample quality. Additionally, we find that learning variances of the reverse diffusion process allows sampling with an order of magnitude fewer forward passes with a negligible difference in sample quality.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the chosen modifications to the noise schedule and variance parameterization do not introduce unmeasured biases in the learned distribution or sampling dynamics beyond what the reported metrics capture.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Targeted tweaks to DDPMs produce competitive likelihoods and high-quality samples, with learned reverse variances enabling 10x faster sampling and predictable scaling with compute.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Simple modifications let denoising diffusion models achieve competitive log-likelihoods while supporting much faster sampling.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2118f6fc99ebc0835cf236c045cbb67c81f02ce3cffb4d1721a9025c2de7ef3f"},"source":{"id":"2102.09672","kind":"arxiv","version":1},"verdict":{"id":"e6030429-ad94-4c1a-b774-cc0fa9ea9572","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T19:15:07.553096Z","strongest_claim":"We show that with a few simple modifications, DDPMs can also achieve competitive log-likelihoods while maintaining high sample quality. Additionally, we find that learning variances of the reverse diffusion process allows sampling with an order of magnitude fewer forward passes with a negligible difference in sample quality.","one_line_summary":"Targeted tweaks to DDPMs produce competitive likelihoods and high-quality samples, with learned reverse variances enabling 10x faster sampling and predictable scaling with compute.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the chosen modifications to the noise schedule and variance parameterization do not introduce unmeasured biases in the learned distribution or sampling dynamics beyond what the reported metrics capture.","pith_extraction_headline":"Simple modifications let denoising diffusion models achieve competitive log-likelihoods while supporting much faster sampling."},"references":{"count":17,"sample":[{"doi":"","year":null,"title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","work_id":"244e6f06-bad2-4f34-8186-ff370286427f","ref_index":1,"cited_arxiv_id":"1809.11096","is_internal_anchor":true},{"doi":"","year":2011,"title":"Very deep vaes generalize autoregressive models and can outperform them on images","work_id":"214ff54a-9ea1-46bc-94a9-8daf75f1d2b9","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","work_id":"ee703933-f9ee-4a48-8621-5b66c0322d6d","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1902,"title":"Flow++: Improving flow-based generative models with variational dequantization and architecture design","work_id":"58dad468-996a-4b27-af63-673e9a09dfe9","ref_index":4,"cited_arxiv_id":"1902.00275","is_internal_anchor":true},{"doi":"","year":2009,"title":"Kynk¨a¨anniemi, T., Karras, T., Laine, S., Lehtinen, J., and Aila, T","work_id":"57a3305f-67e0-48e5-b939-33ac062b4b60","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":17,"snapshot_sha256":"8c6f8996e9a08ce74790d6a0faa84ff44c437f9badfc692f93d43c6244e6722e","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d76da9291b9c1eaf4f5b75f28ef3a0f2bdd14086981db0298a76c4bc840cacf5"},"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":"2102.09672","created_at":"2026-05-17T23:38:46.861621+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.09672v1","created_at":"2026-05-17T23:38:46.861621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.09672","created_at":"2026-05-17T23:38:46.861621+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGWSAIGBGVXM","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGWSAIGBGVXMX4WG","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGWSAIGB","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":25,"sample":[{"citing_arxiv_id":"2502.05909","citing_title":"Towards a Universal Foundation Model for Protein Dynamics: A Multi-Chain Tree-Structured Framework with Transformer Propagators","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2503.21432","citing_title":"Exploring the flavor structure of leptons via diffusion models","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02889","citing_title":"Rethinking Forward Processes for Score-Based Nonlinear Data Assimilation in High Dimensions","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20267","citing_title":"Generation of Heterogeneous PET Images from Uniform Organ Activity Maps Using a Pretrained Domain-Adapted Diffusion Model","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20780","citing_title":"Learning to Think in Physics: Breaking Shortcut Learning in Scientific Diffusion via Representation Alignment","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2310.14189","citing_title":"Improved Techniques for Training Consistency Models","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2511.07571","citing_title":"Forecasting implied volatility surface with generative diffusion models","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2512.23748","citing_title":"A Review of Diffusion-based Simulation-Based Inference: Foundations and Applications in Non-Ideal Data Scenarios","ref_index":69,"is_internal_anchor":true},{"citing_arxiv_id":"2305.02463","citing_title":"Shap-E: Generating Conditional 3D Implicit Functions","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2603.10093","citing_title":"Equivariant Asynchronous Diffusion: An Adaptive Denoising Schedule for Accelerated Molecular Conformation Generation","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02889","citing_title":"Rethinking Forward Processes for Score-Based Nonlinear Data Assimilation in High Dimensions","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2105.05233","citing_title":"Diffusion Models Beat GANs on Image Synthesis","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2205.11487","citing_title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24347","citing_title":"Semantic Segmentation for Histopathology using Learned Regularization based on Global Proportions","ref_index":62,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05689","citing_title":"GCCM: Enhancing Generative Graph Prediction via Contrastive Consistency Model","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01542","citing_title":"Mesh Based Simulations with Spatial and Temporal awareness","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20041","citing_title":"Normalizing Flows with Iterative Denoising","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18966","citing_title":"Self-Improving Tabular Language Models via Iterative Reward-Guided Post-Training","ref_index":175,"is_internal_anchor":true},{"citing_arxiv_id":"2112.10741","citing_title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06829","citing_title":"A Unified Measure-Theoretic View of Diffusion, Score-Based, and Flow Matching Generative Models","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05257","citing_title":"Extending Tabular Denoising Diffusion Probabilistic Models for Time-Series Data Generation","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2204.06125","citing_title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12992","citing_title":"Causal Diffusion Models for Counterfactual Outcome Distributions in Longitudinal Data","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14570","citing_title":"Deepfake Detection Generalization with Diffusion Noise","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17706","citing_title":"OmniVLA-RL: A Vision-Language-Action Model with Spatial Understanding and Online RL","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GGWSAIGBGVXMX4WGGWPUD4IG5Q","json":"https://pith.science/pith/GGWSAIGBGVXMX4WGGWPUD4IG5Q.json","graph_json":"https://pith.science/api/pith-number/GGWSAIGBGVXMX4WGGWPUD4IG5Q/graph.json","events_json":"https://pith.science/api/pith-number/GGWSAIGBGVXMX4WGGWPUD4IG5Q/events.json","paper":"https://pith.science/paper/GGWSAIGB"},"agent_actions":{"view_html":"https://pith.science/pith/GGWSAIGBGVXMX4WGGWPUD4IG5Q","download_json":"https://pith.science/pith/GGWSAIGBGVXMX4WGGWPUD4IG5Q.json","view_paper":"https://pith.science/paper/GGWSAIGB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.09672&json=true","fetch_graph":"https://pith.science/api/pith-number/GGWSAIGBGVXMX4WGGWPUD4IG5Q/graph.json","fetch_events":"https://pith.science/api/pith-number/GGWSAIGBGVXMX4WGGWPUD4IG5Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGWSAIGBGVXMX4WGGWPUD4IG5Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGWSAIGBGVXMX4WGGWPUD4IG5Q/action/storage_attestation","attest_author":"https://pith.science/pith/GGWSAIGBGVXMX4WGGWPUD4IG5Q/action/author_attestation","sign_citation":"https://pith.science/pith/GGWSAIGBGVXMX4WGGWPUD4IG5Q/action/citation_signature","submit_replication":"https://pith.science/pith/GGWSAIGBGVXMX4WGGWPUD4IG5Q/action/replication_record"}},"created_at":"2026-05-17T23:38:46.861621+00:00","updated_at":"2026-05-17T23:38:46.861621+00:00"}