{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YGR6YR4B6PAKQROYRXM3E6WYH5","short_pith_number":"pith:YGR6YR4B","schema_version":"1.0","canonical_sha256":"c1a3ec4781f3c0a845d88dd9b27ad83f6226e68b2199a5fd465fb479766e974f","source":{"kind":"arxiv","id":"2204.13902","version":4},"attestation_state":"computed","paper":{"title":"Fast Sampling of Diffusion Models with Exponential Integrator","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Qinsheng Zhang, Yongxin Chen","submitted_at":"2022-04-29T06:32:38Z","abstract_excerpt":"The past few years have witnessed the great success of Diffusion models~(DMs) in generating high-fidelity samples in generative modeling tasks. A major limitation of the DM is its notoriously slow sampling procedure which normally requires hundreds to thousands of time discretization steps of the learned diffusion process to reach the desired accuracy. Our goal is to develop a fast sampling method for DMs with a much less number of steps while retaining high sample quality. To this end, we systematically analyze the sampling procedure in DMs and identify key factors that affect the sample qual"},"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":"2204.13902","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-29T06:32:38Z","cross_cats_sorted":[],"title_canon_sha256":"e55ca58f5859ebc41ac38b66b5d43a6ae365c5f0b06956efe36a1837caef7437","abstract_canon_sha256":"27070655ff61e76a4242e1bd17911b131eb52a0b7bb4755bfeca87abc629a5ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:27.884440Z","signature_b64":"rHrnUCwJ81dpltpIxZo8QIVQKglBuzyPOJFg+GUrgqaU3BCiQH1hSjCgKWewGobGJphKLcnH7mrWPXD1IFeDDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1a3ec4781f3c0a845d88dd9b27ad83f6226e68b2199a5fd465fb479766e974f","last_reissued_at":"2026-07-05T05:45:27.883943Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:27.883943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast Sampling of Diffusion Models with Exponential Integrator","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Qinsheng Zhang, Yongxin Chen","submitted_at":"2022-04-29T06:32:38Z","abstract_excerpt":"The past few years have witnessed the great success of Diffusion models~(DMs) in generating high-fidelity samples in generative modeling tasks. A major limitation of the DM is its notoriously slow sampling procedure which normally requires hundreds to thousands of time discretization steps of the learned diffusion process to reach the desired accuracy. Our goal is to develop a fast sampling method for DMs with a much less number of steps while retaining high sample quality. To this end, we systematically analyze the sampling procedure in DMs and identify key factors that affect the sample qual"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.13902","kind":"arxiv","version":4},"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/2204.13902/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":"2204.13902","created_at":"2026-07-05T05:45:27.883998+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.13902v4","created_at":"2026-07-05T05:45:27.883998+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.13902","created_at":"2026-07-05T05:45:27.883998+00:00"},{"alias_kind":"pith_short_12","alias_value":"YGR6YR4B6PAK","created_at":"2026-07-05T05:45:27.883998+00:00"},{"alias_kind":"pith_short_16","alias_value":"YGR6YR4B6PAKQROY","created_at":"2026-07-05T05:45:27.883998+00:00"},{"alias_kind":"pith_short_8","alias_value":"YGR6YR4B","created_at":"2026-07-05T05:45:27.883998+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":26,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26285","citing_title":"TEMPO-Diffusion: Temporally Exposed Malicious Poisoning of Diffusion Models","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27377","citing_title":"DanceOPD: On-Policy Generative Field Distillation","ref_index":109,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23898","citing_title":"ARIA: Adaptive Region-Based Importance Allocation for Conditional Diffusion Distillation","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21982","citing_title":"CoDMD: Copula-aware Distribution Matching Distillation for Fast Video Generation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13366","citing_title":"Dual-Constrained Diffusion Image Compression for Operational Rate-Distortion-Perception Optimization","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30332","citing_title":"Colored Noise Diffusion Sampling","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23522","citing_title":"Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2509.01629","citing_title":"Lipschitz-Guided Design of Interpolation Schedules in Generative Models","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2310.14189","citing_title":"Improved Techniques for Training Consistency Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17733","citing_title":"Divergence-Suppressing Couplings for Rectified Flow","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17546","citing_title":"Accelerating Redshift-Conditioned Galaxy Image Synthesis with One-step Generative Modeling","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2506.05398","citing_title":"2ndMatch: Finetuning Pruned Diffusion Models via Second-Order Jacobian Matching","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2510.08431","citing_title":"Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2211.01095","citing_title":"DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2211.01324","citing_title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2603.26357","citing_title":"MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13278","citing_title":"Proximal-Based Generative Modeling for Bayesian Inverse Problems","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2206.00364","citing_title":"Elucidating the Design Space of Diffusion-Based Generative Models","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2509.16117","citing_title":"DiffusionNFT: Online Diffusion Reinforcement with Forward Process","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2303.01469","citing_title":"Consistency Models","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22379","citing_title":"Efficient Diffusion Distillation via Embedding Loss","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04569","citing_title":"LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention","ref_index":232,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00935","citing_title":"Watch Your Step: Information Injection in Diffusion Models via Shadow Timestep Embedding","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10857","citing_title":"Query Lower Bounds for Diffusion Sampling","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2209.03003","citing_title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","ref_index":94,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YGR6YR4B6PAKQROYRXM3E6WYH5","json":"https://pith.science/pith/YGR6YR4B6PAKQROYRXM3E6WYH5.json","graph_json":"https://pith.science/api/pith-number/YGR6YR4B6PAKQROYRXM3E6WYH5/graph.json","events_json":"https://pith.science/api/pith-number/YGR6YR4B6PAKQROYRXM3E6WYH5/events.json","paper":"https://pith.science/paper/YGR6YR4B"},"agent_actions":{"view_html":"https://pith.science/pith/YGR6YR4B6PAKQROYRXM3E6WYH5","download_json":"https://pith.science/pith/YGR6YR4B6PAKQROYRXM3E6WYH5.json","view_paper":"https://pith.science/paper/YGR6YR4B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.13902&json=true","fetch_graph":"https://pith.science/api/pith-number/YGR6YR4B6PAKQROYRXM3E6WYH5/graph.json","fetch_events":"https://pith.science/api/pith-number/YGR6YR4B6PAKQROYRXM3E6WYH5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YGR6YR4B6PAKQROYRXM3E6WYH5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YGR6YR4B6PAKQROYRXM3E6WYH5/action/storage_attestation","attest_author":"https://pith.science/pith/YGR6YR4B6PAKQROYRXM3E6WYH5/action/author_attestation","sign_citation":"https://pith.science/pith/YGR6YR4B6PAKQROYRXM3E6WYH5/action/citation_signature","submit_replication":"https://pith.science/pith/YGR6YR4B6PAKQROYRXM3E6WYH5/action/replication_record"}},"created_at":"2026-07-05T05:45:27.883998+00:00","updated_at":"2026-07-05T05:45:27.883998+00:00"}