{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZMI5DU3KO2ZQ5UGLMTFHTLMCM2","short_pith_number":"pith:ZMI5DU3K","schema_version":"1.0","canonical_sha256":"cb11d1d36a76b30ed0cb64ca79ad8266a598e3811d26594386df70225582be1f","source":{"kind":"arxiv","id":"2404.12382","version":1},"attestation_state":"computed","paper":{"title":"Lazy Diffusion Transformer for Interactive Image Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Daniel Cohen-Or, Eli Shechtman, Micha\\\"el Gharbi, Richard Zhang, Taesung Park, Yotam Nitzan, Zongze Wu","submitted_at":"2024-04-18T17:59:27Z","abstract_excerpt":"We introduce a novel diffusion transformer, LazyDiffusion, that generates partial image updates efficiently. Our approach targets interactive image editing applications in which, starting from a blank canvas or an image, a user specifies a sequence of localized image modifications using binary masks and text prompts. Our generator operates in two phases. First, a context encoder processes the current canvas and user mask to produce a compact global context tailored to the region to generate. Second, conditioned on this context, a diffusion-based transformer decoder synthesizes the masked pixel"},"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":"2404.12382","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-18T17:59:27Z","cross_cats_sorted":["cs.AI","cs.GR"],"title_canon_sha256":"154b2a61311e1db1fbab03f68a5a181883ca57b2a23fb80c6829414992caf87a","abstract_canon_sha256":"1a2cf3fc94f6264baa81fa223ff7e53ebfb45c449022b78152b6fd83417d62e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:38.987002Z","signature_b64":"++VxKEExZ+hqkFURdRuynP0HcROsxLXaF44Q/uah3YP1QSAInMlr2Asz6QA2puDZ4NVUMxHReNX5L0ym9EMyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb11d1d36a76b30ed0cb64ca79ad8266a598e3811d26594386df70225582be1f","last_reissued_at":"2026-07-05T08:09:38.986473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:38.986473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lazy Diffusion Transformer for Interactive Image Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Daniel Cohen-Or, Eli Shechtman, Micha\\\"el Gharbi, Richard Zhang, Taesung Park, Yotam Nitzan, Zongze Wu","submitted_at":"2024-04-18T17:59:27Z","abstract_excerpt":"We introduce a novel diffusion transformer, LazyDiffusion, that generates partial image updates efficiently. Our approach targets interactive image editing applications in which, starting from a blank canvas or an image, a user specifies a sequence of localized image modifications using binary masks and text prompts. Our generator operates in two phases. First, a context encoder processes the current canvas and user mask to produce a compact global context tailored to the region to generate. Second, conditioned on this context, a diffusion-based transformer decoder synthesizes the masked pixel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12382","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/2404.12382/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":"2404.12382","created_at":"2026-07-05T08:09:38.986542+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.12382v1","created_at":"2026-07-05T08:09:38.986542+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12382","created_at":"2026-07-05T08:09:38.986542+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZMI5DU3KO2ZQ","created_at":"2026-07-05T08:09:38.986542+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZMI5DU3KO2ZQ5UGL","created_at":"2026-07-05T08:09:38.986542+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZMI5DU3K","created_at":"2026-07-05T08:09:38.986542+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15399","citing_title":"Blended Point Cloud Diffusion for Localized Text-guided Shape Editing","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZMI5DU3KO2ZQ5UGLMTFHTLMCM2","json":"https://pith.science/pith/ZMI5DU3KO2ZQ5UGLMTFHTLMCM2.json","graph_json":"https://pith.science/api/pith-number/ZMI5DU3KO2ZQ5UGLMTFHTLMCM2/graph.json","events_json":"https://pith.science/api/pith-number/ZMI5DU3KO2ZQ5UGLMTFHTLMCM2/events.json","paper":"https://pith.science/paper/ZMI5DU3K"},"agent_actions":{"view_html":"https://pith.science/pith/ZMI5DU3KO2ZQ5UGLMTFHTLMCM2","download_json":"https://pith.science/pith/ZMI5DU3KO2ZQ5UGLMTFHTLMCM2.json","view_paper":"https://pith.science/paper/ZMI5DU3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.12382&json=true","fetch_graph":"https://pith.science/api/pith-number/ZMI5DU3KO2ZQ5UGLMTFHTLMCM2/graph.json","fetch_events":"https://pith.science/api/pith-number/ZMI5DU3KO2ZQ5UGLMTFHTLMCM2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZMI5DU3KO2ZQ5UGLMTFHTLMCM2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZMI5DU3KO2ZQ5UGLMTFHTLMCM2/action/storage_attestation","attest_author":"https://pith.science/pith/ZMI5DU3KO2ZQ5UGLMTFHTLMCM2/action/author_attestation","sign_citation":"https://pith.science/pith/ZMI5DU3KO2ZQ5UGLMTFHTLMCM2/action/citation_signature","submit_replication":"https://pith.science/pith/ZMI5DU3KO2ZQ5UGLMTFHTLMCM2/action/replication_record"}},"created_at":"2026-07-05T08:09:38.986542+00:00","updated_at":"2026-07-05T08:09:38.986542+00:00"}