{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FSKMAL4PSCDPCJELGMPF5XJ4LI","short_pith_number":"pith:FSKMAL4P","schema_version":"1.0","canonical_sha256":"2c94c02f8f9086f1248b331e5edd3c5a3a6092d6242165d2f012a1bf46d6cae9","source":{"kind":"arxiv","id":"2106.03802","version":1},"attestation_state":"computed","paper":{"title":"Learning to Efficiently Sample from Diffusion Probabilistic Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Watson, Jonathan Ho, Mohammad Norouzi, William Chan","submitted_at":"2021-06-07T17:15:07Z","abstract_excerpt":"Denoising Diffusion Probabilistic Models (DDPMs) have emerged as a powerful family of generative models that can yield high-fidelity samples and competitive log-likelihoods across a range of domains, including image and speech synthesis. Key advantages of DDPMs include ease of training, in contrast to generative adversarial networks, and speed of generation, in contrast to autoregressive models. However, DDPMs typically require hundreds-to-thousands of steps to generate a high fidelity sample, making them prohibitively expensive for high dimensional problems. Fortunately, DDPMs allow trading g"},"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":"2106.03802","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-07T17:15:07Z","cross_cats_sorted":[],"title_canon_sha256":"60d9a7e9664b54af1e4062bcacfce64781917ff109f5fe24f1b1e410bf227f86","abstract_canon_sha256":"7fd10c01e1e394df392bbf039868763f663e1fa7496cacb034a1e6ece26aec2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:55.688528Z","signature_b64":"mYd3Yv+K7qGSzS4NjEjJuyzGiw4C+gG8MWutpYbtRIFrzop6i1oLTxmiT55nVjofNW6c5hm89Ku3NTycdFvDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c94c02f8f9086f1248b331e5edd3c5a3a6092d6242165d2f012a1bf46d6cae9","last_reissued_at":"2026-07-05T02:46:55.688107Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:55.688107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Efficiently Sample from Diffusion Probabilistic Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Watson, Jonathan Ho, Mohammad Norouzi, William Chan","submitted_at":"2021-06-07T17:15:07Z","abstract_excerpt":"Denoising Diffusion Probabilistic Models (DDPMs) have emerged as a powerful family of generative models that can yield high-fidelity samples and competitive log-likelihoods across a range of domains, including image and speech synthesis. Key advantages of DDPMs include ease of training, in contrast to generative adversarial networks, and speed of generation, in contrast to autoregressive models. However, DDPMs typically require hundreds-to-thousands of steps to generate a high fidelity sample, making them prohibitively expensive for high dimensional problems. Fortunately, DDPMs allow trading g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03802","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.03802/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":"2106.03802","created_at":"2026-07-05T02:46:55.688168+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.03802v1","created_at":"2026-07-05T02:46:55.688168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03802","created_at":"2026-07-05T02:46:55.688168+00:00"},{"alias_kind":"pith_short_12","alias_value":"FSKMAL4PSCDP","created_at":"2026-07-05T02:46:55.688168+00:00"},{"alias_kind":"pith_short_16","alias_value":"FSKMAL4PSCDPCJEL","created_at":"2026-07-05T02:46:55.688168+00:00"},{"alias_kind":"pith_short_8","alias_value":"FSKMAL4P","created_at":"2026-07-05T02:46:55.688168+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06609","citing_title":"D2PO: Optimizing Diffusion Samplers via Dynamic Preference","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2511.11688","citing_title":"Hierarchical Schedule Optimization for Fast and Robust Diffusion Model Sampling","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2506.05398","citing_title":"2ndMatch: Finetuning Pruned Diffusion Models via Second-Order Jacobian Matching","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2206.00364","citing_title":"Elucidating the Design Space of Diffusion-Based Generative Models","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2310.04378","citing_title":"Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11547","citing_title":"Sharpen Your Flow: Sharpness-Aware Sampling for Flow Matching","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2202.00512","citing_title":"Progressive Distillation for Fast Sampling of Diffusion Models","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FSKMAL4PSCDPCJELGMPF5XJ4LI","json":"https://pith.science/pith/FSKMAL4PSCDPCJELGMPF5XJ4LI.json","graph_json":"https://pith.science/api/pith-number/FSKMAL4PSCDPCJELGMPF5XJ4LI/graph.json","events_json":"https://pith.science/api/pith-number/FSKMAL4PSCDPCJELGMPF5XJ4LI/events.json","paper":"https://pith.science/paper/FSKMAL4P"},"agent_actions":{"view_html":"https://pith.science/pith/FSKMAL4PSCDPCJELGMPF5XJ4LI","download_json":"https://pith.science/pith/FSKMAL4PSCDPCJELGMPF5XJ4LI.json","view_paper":"https://pith.science/paper/FSKMAL4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.03802&json=true","fetch_graph":"https://pith.science/api/pith-number/FSKMAL4PSCDPCJELGMPF5XJ4LI/graph.json","fetch_events":"https://pith.science/api/pith-number/FSKMAL4PSCDPCJELGMPF5XJ4LI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FSKMAL4PSCDPCJELGMPF5XJ4LI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FSKMAL4PSCDPCJELGMPF5XJ4LI/action/storage_attestation","attest_author":"https://pith.science/pith/FSKMAL4PSCDPCJELGMPF5XJ4LI/action/author_attestation","sign_citation":"https://pith.science/pith/FSKMAL4PSCDPCJELGMPF5XJ4LI/action/citation_signature","submit_replication":"https://pith.science/pith/FSKMAL4PSCDPCJELGMPF5XJ4LI/action/replication_record"}},"created_at":"2026-07-05T02:46:55.688168+00:00","updated_at":"2026-07-05T02:46:55.688168+00:00"}