{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:R2Z54BJDRO2XKHPKHQMUHPCL4H","short_pith_number":"pith:R2Z54BJD","schema_version":"1.0","canonical_sha256":"8eb3de05238bb5751dea3c1943bc4be1dbdcd3f97aa8a252a73078d7025a86dd","source":{"kind":"arxiv","id":"2506.01430","version":1},"attestation_state":"computed","paper":{"title":"DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenxi Xie, Lei Zhang, Minghan Li, Qiaosi Yi, Shuai Li, Yuhui Wu","submitted_at":"2025-06-02T08:41:33Z","abstract_excerpt":"Leveraging the powerful generation capability of large-scale pretrained text-to-image models, training-free methods have demonstrated impressive image editing results. Conventional diffusion-based methods, as well as recent rectified flow (RF)-based methods, typically reverse synthesis trajectories by gradually adding noise to clean images, during which the noisy latent at the current timestep is used to approximate that at the next timesteps, introducing accumulated drift and degrading reconstruction accuracy. Considering the fact that in RF the noisy latent is estimated through direct interp"},"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":"2506.01430","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T08:41:33Z","cross_cats_sorted":[],"title_canon_sha256":"d7a0bfde86a5fc6ffb188272f5d03a20a2c47d7660ee3cadcb323cea951ba04b","abstract_canon_sha256":"fc9564a4ff6c297739aba8bcf79e65c00d490a34db56a097e7fa8255cacf25e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:13.285856Z","signature_b64":"dxXonuiqIHU1cV0ZfDBzY2HHnW3D2EwDPUu1Sp5jYcNBU7NL9W3s0h8hg6A2MeFQtGK+cxJAuhoo1OPRZ+FjDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8eb3de05238bb5751dea3c1943bc4be1dbdcd3f97aa8a252a73078d7025a86dd","last_reissued_at":"2026-07-05T11:14:13.285097Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:13.285097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenxi Xie, Lei Zhang, Minghan Li, Qiaosi Yi, Shuai Li, Yuhui Wu","submitted_at":"2025-06-02T08:41:33Z","abstract_excerpt":"Leveraging the powerful generation capability of large-scale pretrained text-to-image models, training-free methods have demonstrated impressive image editing results. Conventional diffusion-based methods, as well as recent rectified flow (RF)-based methods, typically reverse synthesis trajectories by gradually adding noise to clean images, during which the noisy latent at the current timestep is used to approximate that at the next timesteps, introducing accumulated drift and degrading reconstruction accuracy. Considering the fact that in RF the noisy latent is estimated through direct interp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01430","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/2506.01430/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":"2506.01430","created_at":"2026-07-05T11:14:13.285188+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01430v1","created_at":"2026-07-05T11:14:13.285188+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01430","created_at":"2026-07-05T11:14:13.285188+00:00"},{"alias_kind":"pith_short_12","alias_value":"R2Z54BJDRO2X","created_at":"2026-07-05T11:14:13.285188+00:00"},{"alias_kind":"pith_short_16","alias_value":"R2Z54BJDRO2XKHPK","created_at":"2026-07-05T11:14:13.285188+00:00"},{"alias_kind":"pith_short_8","alias_value":"R2Z54BJD","created_at":"2026-07-05T11:14:13.285188+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10319","citing_title":"LimeCross: Context-Conditioned Layered Image Editing with Structural Consistency","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15871","citing_title":"UniEditBench: A Unified and Cost-Effective Benchmark for Image and Video Editing via Distilled MLLMs","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02417","citing_title":"DirectEdit: Step-Level Accurate Inversion for Flow-Based Image Editing","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R2Z54BJDRO2XKHPKHQMUHPCL4H","json":"https://pith.science/pith/R2Z54BJDRO2XKHPKHQMUHPCL4H.json","graph_json":"https://pith.science/api/pith-number/R2Z54BJDRO2XKHPKHQMUHPCL4H/graph.json","events_json":"https://pith.science/api/pith-number/R2Z54BJDRO2XKHPKHQMUHPCL4H/events.json","paper":"https://pith.science/paper/R2Z54BJD"},"agent_actions":{"view_html":"https://pith.science/pith/R2Z54BJDRO2XKHPKHQMUHPCL4H","download_json":"https://pith.science/pith/R2Z54BJDRO2XKHPKHQMUHPCL4H.json","view_paper":"https://pith.science/paper/R2Z54BJD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01430&json=true","fetch_graph":"https://pith.science/api/pith-number/R2Z54BJDRO2XKHPKHQMUHPCL4H/graph.json","fetch_events":"https://pith.science/api/pith-number/R2Z54BJDRO2XKHPKHQMUHPCL4H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R2Z54BJDRO2XKHPKHQMUHPCL4H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R2Z54BJDRO2XKHPKHQMUHPCL4H/action/storage_attestation","attest_author":"https://pith.science/pith/R2Z54BJDRO2XKHPKHQMUHPCL4H/action/author_attestation","sign_citation":"https://pith.science/pith/R2Z54BJDRO2XKHPKHQMUHPCL4H/action/citation_signature","submit_replication":"https://pith.science/pith/R2Z54BJDRO2XKHPKHQMUHPCL4H/action/replication_record"}},"created_at":"2026-07-05T11:14:13.285188+00:00","updated_at":"2026-07-05T11:14:13.285188+00:00"}