{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:F2WM47RKB723KHZHOTWK2NQIZS","short_pith_number":"pith:F2WM47RK","schema_version":"1.0","canonical_sha256":"2eacce7e2a0ff5b51f2774ecad3608ccb5b9ca7e15374187bdf74fc0e0b060a1","source":{"kind":"arxiv","id":"2106.15282","version":3},"attestation_state":"computed","paper":{"title":"Cascaded Diffusion Models for High Fidelity Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chitwan Saharia, David J. Fleet, Jonathan Ho, Mohammad Norouzi, Tim Salimans, William Chan","submitted_at":"2021-05-30T17:14:52Z","abstract_excerpt":"We show that cascaded diffusion models are capable of generating high fidelity images on the class-conditional ImageNet generation benchmark, without any assistance from auxiliary image classifiers to boost sample quality. A cascaded diffusion model comprises a pipeline of multiple diffusion models that generate images of increasing resolution, beginning with a standard diffusion model at the lowest resolution, followed by one or more super-resolution diffusion models that successively upsample the image and add higher resolution details. We find that the sample quality of a cascading pipeline"},"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":"2106.15282","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-30T17:14:52Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b7235407111a9d387d92a63e553956b4450de6d58d5a250bdc5d2b268fbed3a8","abstract_canon_sha256":"8ce559d233ff2910500f989a29d75a814ee5d72d2a2919140ccc3fa0c7741611"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:41:39.879022Z","signature_b64":"K63QWxFt+UHvS0ks8o9BZlHhc43Vm7s0WxE0iMRQMuiJCSQ54GxOKv3fm69ePyKUgzIf7YpiZrACzMMfd9oLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2eacce7e2a0ff5b51f2774ecad3608ccb5b9ca7e15374187bdf74fc0e0b060a1","last_reissued_at":"2026-07-05T03:41:39.878552Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:41:39.878552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cascaded Diffusion Models for High Fidelity Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chitwan Saharia, David J. Fleet, Jonathan Ho, Mohammad Norouzi, Tim Salimans, William Chan","submitted_at":"2021-05-30T17:14:52Z","abstract_excerpt":"We show that cascaded diffusion models are capable of generating high fidelity images on the class-conditional ImageNet generation benchmark, without any assistance from auxiliary image classifiers to boost sample quality. A cascaded diffusion model comprises a pipeline of multiple diffusion models that generate images of increasing resolution, beginning with a standard diffusion model at the lowest resolution, followed by one or more super-resolution diffusion models that successively upsample the image and add higher resolution details. We find that the sample quality of a cascading pipeline"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.15282","kind":"arxiv","version":3},"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/2106.15282/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":"2106.15282","created_at":"2026-07-05T03:41:39.878614+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.15282v3","created_at":"2026-07-05T03:41:39.878614+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.15282","created_at":"2026-07-05T03:41:39.878614+00:00"},{"alias_kind":"pith_short_12","alias_value":"F2WM47RKB723","created_at":"2026-07-05T03:41:39.878614+00:00"},{"alias_kind":"pith_short_16","alias_value":"F2WM47RKB723KHZH","created_at":"2026-07-05T03:41:39.878614+00:00"},{"alias_kind":"pith_short_8","alias_value":"F2WM47RK","created_at":"2026-07-05T03:41:39.878614+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24690","citing_title":"Sum of Costs Diffusion with Dynamic Guidance for Motion Planning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21042","citing_title":"Dynamic Video Generation: Shaping Video Generation Across Time and Space","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2408.14837","citing_title":"Diffusion Models Are Real-Time Game Engines","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2204.03458","citing_title":"Video Diffusion Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2212.09748","citing_title":"Scalable Diffusion Models with Transformers","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2112.10752","citing_title":"High-Resolution Image Synthesis with Latent Diffusion Models","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2202.00512","citing_title":"Progressive Distillation for Fast Sampling of Diffusion Models","ref_index":5,"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":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09715","citing_title":"MuPPet: Multi-person 2D-to-3D Pose Lifting","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2311.15127","citing_title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2204.06125","citing_title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2207.12598","citing_title":"Classifier-Free Diffusion Guidance","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F2WM47RKB723KHZHOTWK2NQIZS","json":"https://pith.science/pith/F2WM47RKB723KHZHOTWK2NQIZS.json","graph_json":"https://pith.science/api/pith-number/F2WM47RKB723KHZHOTWK2NQIZS/graph.json","events_json":"https://pith.science/api/pith-number/F2WM47RKB723KHZHOTWK2NQIZS/events.json","paper":"https://pith.science/paper/F2WM47RK"},"agent_actions":{"view_html":"https://pith.science/pith/F2WM47RKB723KHZHOTWK2NQIZS","download_json":"https://pith.science/pith/F2WM47RKB723KHZHOTWK2NQIZS.json","view_paper":"https://pith.science/paper/F2WM47RK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.15282&json=true","fetch_graph":"https://pith.science/api/pith-number/F2WM47RKB723KHZHOTWK2NQIZS/graph.json","fetch_events":"https://pith.science/api/pith-number/F2WM47RKB723KHZHOTWK2NQIZS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F2WM47RKB723KHZHOTWK2NQIZS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F2WM47RKB723KHZHOTWK2NQIZS/action/storage_attestation","attest_author":"https://pith.science/pith/F2WM47RKB723KHZHOTWK2NQIZS/action/author_attestation","sign_citation":"https://pith.science/pith/F2WM47RKB723KHZHOTWK2NQIZS/action/citation_signature","submit_replication":"https://pith.science/pith/F2WM47RKB723KHZHOTWK2NQIZS/action/replication_record"}},"created_at":"2026-07-05T03:41:39.878614+00:00","updated_at":"2026-07-05T03:41:39.878614+00:00"}