{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HIOHGIYOHFJTAM26WNYZN6PMLW","short_pith_number":"pith:HIOHGIYO","schema_version":"1.0","canonical_sha256":"3a1c73230e395330335eb37196f9ec5d85bfb4e8d9b21bf2dcf4400a2fb281ba","source":{"kind":"arxiv","id":"2411.03286","version":2},"attestation_state":"computed","paper":{"title":"DiT4Edit: Diffusion Transformer for Image Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyuan Wang, Chenyang Qi, Haozhe Chen, Kunyu Feng, Qifeng Chen, Yue Ma, Zeyu Wang","submitted_at":"2024-11-05T17:35:41Z","abstract_excerpt":"Despite recent advances in UNet-based image editing, methods for shape-aware object editing in high-resolution images are still lacking. Compared to UNet, Diffusion Transformers (DiT) demonstrate superior capabilities to effectively capture the long-range dependencies among patches, leading to higher-quality image generation. In this paper, we propose DiT4Edit, the first Diffusion Transformer-based image editing framework. Specifically, DiT4Edit uses the DPM-Solver inversion algorithm to obtain the inverted latents, reducing the number of steps compared to the DDIM inversion algorithm commonly"},"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":"2411.03286","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-05T17:35:41Z","cross_cats_sorted":[],"title_canon_sha256":"32acdf9d1bfd9625898bba2ea966ceea41fcd920fe8647d20680ffb8f544b780","abstract_canon_sha256":"d751d8387ca89dbb572b6531139b0b0c28710c8bfbedfe7ce5c9200308b205d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:13.725333Z","signature_b64":"tNVUQvXDphOx+PdzjQ/HD2tFRzwAO5rf0D3GzcAZmiDKruFr2395r8NFIcAUeigsZHKKbQ1W4Urk7d51miq/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a1c73230e395330335eb37196f9ec5d85bfb4e8d9b21bf2dcf4400a2fb281ba","last_reissued_at":"2026-07-05T09:32:13.724860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:13.724860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiT4Edit: Diffusion Transformer for Image Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyuan Wang, Chenyang Qi, Haozhe Chen, Kunyu Feng, Qifeng Chen, Yue Ma, Zeyu Wang","submitted_at":"2024-11-05T17:35:41Z","abstract_excerpt":"Despite recent advances in UNet-based image editing, methods for shape-aware object editing in high-resolution images are still lacking. Compared to UNet, Diffusion Transformers (DiT) demonstrate superior capabilities to effectively capture the long-range dependencies among patches, leading to higher-quality image generation. In this paper, we propose DiT4Edit, the first Diffusion Transformer-based image editing framework. Specifically, DiT4Edit uses the DPM-Solver inversion algorithm to obtain the inverted latents, reducing the number of steps compared to the DDIM inversion algorithm commonly"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03286","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/2411.03286/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":"2411.03286","created_at":"2026-07-05T09:32:13.724913+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.03286v2","created_at":"2026-07-05T09:32:13.724913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03286","created_at":"2026-07-05T09:32:13.724913+00:00"},{"alias_kind":"pith_short_12","alias_value":"HIOHGIYOHFJT","created_at":"2026-07-05T09:32:13.724913+00:00"},{"alias_kind":"pith_short_16","alias_value":"HIOHGIYOHFJTAM26","created_at":"2026-07-05T09:32:13.724913+00:00"},{"alias_kind":"pith_short_8","alias_value":"HIOHGIYO","created_at":"2026-07-05T09:32:13.724913+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.20505","citing_title":"Describe, Don't Dictate: Semantic Image Editing with Natural Language Intent","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HIOHGIYOHFJTAM26WNYZN6PMLW","json":"https://pith.science/pith/HIOHGIYOHFJTAM26WNYZN6PMLW.json","graph_json":"https://pith.science/api/pith-number/HIOHGIYOHFJTAM26WNYZN6PMLW/graph.json","events_json":"https://pith.science/api/pith-number/HIOHGIYOHFJTAM26WNYZN6PMLW/events.json","paper":"https://pith.science/paper/HIOHGIYO"},"agent_actions":{"view_html":"https://pith.science/pith/HIOHGIYOHFJTAM26WNYZN6PMLW","download_json":"https://pith.science/pith/HIOHGIYOHFJTAM26WNYZN6PMLW.json","view_paper":"https://pith.science/paper/HIOHGIYO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.03286&json=true","fetch_graph":"https://pith.science/api/pith-number/HIOHGIYOHFJTAM26WNYZN6PMLW/graph.json","fetch_events":"https://pith.science/api/pith-number/HIOHGIYOHFJTAM26WNYZN6PMLW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HIOHGIYOHFJTAM26WNYZN6PMLW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HIOHGIYOHFJTAM26WNYZN6PMLW/action/storage_attestation","attest_author":"https://pith.science/pith/HIOHGIYOHFJTAM26WNYZN6PMLW/action/author_attestation","sign_citation":"https://pith.science/pith/HIOHGIYOHFJTAM26WNYZN6PMLW/action/citation_signature","submit_replication":"https://pith.science/pith/HIOHGIYOHFJTAM26WNYZN6PMLW/action/replication_record"}},"created_at":"2026-07-05T09:32:13.724913+00:00","updated_at":"2026-07-05T09:32:13.724913+00:00"}