{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LMXQST3WASL2TAEG5X7ZIPUMBF","short_pith_number":"pith:LMXQST3W","schema_version":"1.0","canonical_sha256":"5b2f094f760497a98086edff943e8c094f016c4ac7a85740b7147dc6f3d87852","source":{"kind":"arxiv","id":"2310.15111","version":2},"attestation_state":"computed","paper":{"title":"Matryoshka Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiatao Gu, Josh Susskind, Navdeep Jaitly, Shuangfei Zhai, Yizhe Zhang","submitted_at":"2023-10-23T17:20:01Z","abstract_excerpt":"Diffusion models are the de facto approach for generating high-quality images and videos, but learning high-dimensional models remains a formidable task due to computational and optimization challenges. Existing methods often resort to training cascaded models in pixel space or using a downsampled latent space of a separately trained auto-encoder. In this paper, we introduce Matryoshka Diffusion Models(MDM), an end-to-end framework for high-resolution image and video synthesis. We propose a diffusion process that denoises inputs at multiple resolutions jointly and uses a NestedUNet architectur"},"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":"2310.15111","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-23T17:20:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cc4518e8881b4c5c21849aedbf315b4ed1762a2703e0d1c76f7bb36e52f2c0de","abstract_canon_sha256":"d3425f4839dba3514e3a8605136bfe132c0602443d74dffd9665ad808a41459d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:26.706998Z","signature_b64":"Jig2rPukwkNjKHzLBeWYS8Pj+mSFNAPRHXFCz38WMn7/0zRfEGnrgVqwe5yyLV19jpq2Nk6gjpAJTgnRcn0WDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b2f094f760497a98086edff943e8c094f016c4ac7a85740b7147dc6f3d87852","last_reissued_at":"2026-07-05T09:01:26.706604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:26.706604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Matryoshka Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiatao Gu, Josh Susskind, Navdeep Jaitly, Shuangfei Zhai, Yizhe Zhang","submitted_at":"2023-10-23T17:20:01Z","abstract_excerpt":"Diffusion models are the de facto approach for generating high-quality images and videos, but learning high-dimensional models remains a formidable task due to computational and optimization challenges. Existing methods often resort to training cascaded models in pixel space or using a downsampled latent space of a separately trained auto-encoder. In this paper, we introduce Matryoshka Diffusion Models(MDM), an end-to-end framework for high-resolution image and video synthesis. We propose a diffusion process that denoises inputs at multiple resolutions jointly and uses a NestedUNet architectur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15111","kind":"arxiv","version":2},"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/2310.15111/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":"2310.15111","created_at":"2026-07-05T09:01:26.706660+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.15111v2","created_at":"2026-07-05T09:01:26.706660+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15111","created_at":"2026-07-05T09:01:26.706660+00:00"},{"alias_kind":"pith_short_12","alias_value":"LMXQST3WASL2","created_at":"2026-07-05T09:01:26.706660+00:00"},{"alias_kind":"pith_short_16","alias_value":"LMXQST3WASL2TAEG","created_at":"2026-07-05T09:01:26.706660+00:00"},{"alias_kind":"pith_short_8","alias_value":"LMXQST3W","created_at":"2026-07-05T09:01:26.706660+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.24374","citing_title":"MIPIC: Matryoshka Representation Learning via Self-Distilled Intra-Relational and Progressive Information Chaining","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LMXQST3WASL2TAEG5X7ZIPUMBF","json":"https://pith.science/pith/LMXQST3WASL2TAEG5X7ZIPUMBF.json","graph_json":"https://pith.science/api/pith-number/LMXQST3WASL2TAEG5X7ZIPUMBF/graph.json","events_json":"https://pith.science/api/pith-number/LMXQST3WASL2TAEG5X7ZIPUMBF/events.json","paper":"https://pith.science/paper/LMXQST3W"},"agent_actions":{"view_html":"https://pith.science/pith/LMXQST3WASL2TAEG5X7ZIPUMBF","download_json":"https://pith.science/pith/LMXQST3WASL2TAEG5X7ZIPUMBF.json","view_paper":"https://pith.science/paper/LMXQST3W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.15111&json=true","fetch_graph":"https://pith.science/api/pith-number/LMXQST3WASL2TAEG5X7ZIPUMBF/graph.json","fetch_events":"https://pith.science/api/pith-number/LMXQST3WASL2TAEG5X7ZIPUMBF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LMXQST3WASL2TAEG5X7ZIPUMBF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LMXQST3WASL2TAEG5X7ZIPUMBF/action/storage_attestation","attest_author":"https://pith.science/pith/LMXQST3WASL2TAEG5X7ZIPUMBF/action/author_attestation","sign_citation":"https://pith.science/pith/LMXQST3WASL2TAEG5X7ZIPUMBF/action/citation_signature","submit_replication":"https://pith.science/pith/LMXQST3WASL2TAEG5X7ZIPUMBF/action/replication_record"}},"created_at":"2026-07-05T09:01:26.706660+00:00","updated_at":"2026-07-05T09:01:26.706660+00:00"}