{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:J3LWNO2JLJQQRA2HWC57PKEQNA","short_pith_number":"pith:J3LWNO2J","schema_version":"1.0","canonical_sha256":"4ed766bb495a61088347b0bbf7a8906811d91217d91faf3312a0d9c26a6ca8c3","source":{"kind":"arxiv","id":"2210.00939","version":6},"attestation_state":"computed","paper":{"title":"Improving Sample Quality of Diffusion Models Using Self-Attention Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Gyuseong Lee, Seungryong Kim, Susung Hong, Wooseok Jang","submitted_at":"2022-10-03T13:50:58Z","abstract_excerpt":"Denoising diffusion models (DDMs) have attracted attention for their exceptional generation quality and diversity. This success is largely attributed to the use of class- or text-conditional diffusion guidance methods, such as classifier and classifier-free guidance. In this paper, we present a more comprehensive perspective that goes beyond the traditional guidance methods. From this generalized perspective, we introduce novel condition- and training-free strategies to enhance the quality of generated images. As a simple solution, blur guidance improves the suitability of intermediate samples"},"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":"2210.00939","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-03T13:50:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4cf28c2057145d83a2281ef56f246a5083cb140283bbdeb2790285691d366ee1","abstract_canon_sha256":"82c18f540d4489a4cf4696142ae8c5b11ef1d6e97482ec13cc08f3259e107f5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:18.982696Z","signature_b64":"yI6vfSfdFtFQHasxia/9nW4bhM9HcWtJ3+WYgTLA4++eNNJFkjSw1Ub7SdnEt7sITHqroP4qdysogc+vVpvuBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ed766bb495a61088347b0bbf7a8906811d91217d91faf3312a0d9c26a6ca8c3","last_reissued_at":"2026-07-05T06:44:18.982148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:18.982148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Sample Quality of Diffusion Models Using Self-Attention Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Gyuseong Lee, Seungryong Kim, Susung Hong, Wooseok Jang","submitted_at":"2022-10-03T13:50:58Z","abstract_excerpt":"Denoising diffusion models (DDMs) have attracted attention for their exceptional generation quality and diversity. This success is largely attributed to the use of class- or text-conditional diffusion guidance methods, such as classifier and classifier-free guidance. In this paper, we present a more comprehensive perspective that goes beyond the traditional guidance methods. From this generalized perspective, we introduce novel condition- and training-free strategies to enhance the quality of generated images. As a simple solution, blur guidance improves the suitability of intermediate samples"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.00939","kind":"arxiv","version":6},"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/2210.00939/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":"2210.00939","created_at":"2026-07-05T06:44:18.982210+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.00939v6","created_at":"2026-07-05T06:44:18.982210+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00939","created_at":"2026-07-05T06:44:18.982210+00:00"},{"alias_kind":"pith_short_12","alias_value":"J3LWNO2JLJQQ","created_at":"2026-07-05T06:44:18.982210+00:00"},{"alias_kind":"pith_short_16","alias_value":"J3LWNO2JLJQQRA2H","created_at":"2026-07-05T06:44:18.982210+00:00"},{"alias_kind":"pith_short_8","alias_value":"J3LWNO2J","created_at":"2026-07-05T06:44:18.982210+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.09216","citing_title":"Controllable protein design with particle-based Feynman-Kac steering","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J3LWNO2JLJQQRA2HWC57PKEQNA","json":"https://pith.science/pith/J3LWNO2JLJQQRA2HWC57PKEQNA.json","graph_json":"https://pith.science/api/pith-number/J3LWNO2JLJQQRA2HWC57PKEQNA/graph.json","events_json":"https://pith.science/api/pith-number/J3LWNO2JLJQQRA2HWC57PKEQNA/events.json","paper":"https://pith.science/paper/J3LWNO2J"},"agent_actions":{"view_html":"https://pith.science/pith/J3LWNO2JLJQQRA2HWC57PKEQNA","download_json":"https://pith.science/pith/J3LWNO2JLJQQRA2HWC57PKEQNA.json","view_paper":"https://pith.science/paper/J3LWNO2J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.00939&json=true","fetch_graph":"https://pith.science/api/pith-number/J3LWNO2JLJQQRA2HWC57PKEQNA/graph.json","fetch_events":"https://pith.science/api/pith-number/J3LWNO2JLJQQRA2HWC57PKEQNA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J3LWNO2JLJQQRA2HWC57PKEQNA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J3LWNO2JLJQQRA2HWC57PKEQNA/action/storage_attestation","attest_author":"https://pith.science/pith/J3LWNO2JLJQQRA2HWC57PKEQNA/action/author_attestation","sign_citation":"https://pith.science/pith/J3LWNO2JLJQQRA2HWC57PKEQNA/action/citation_signature","submit_replication":"https://pith.science/pith/J3LWNO2JLJQQRA2HWC57PKEQNA/action/replication_record"}},"created_at":"2026-07-05T06:44:18.982210+00:00","updated_at":"2026-07-05T06:44:18.982210+00:00"}