{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Q5VY6QLM2TQT6RI7I4YFEY53NH","short_pith_number":"pith:Q5VY6QLM","schema_version":"1.0","canonical_sha256":"876b8f416cd4e13f451f47305263bb69ef777631436c36a86f54687cc4bf4ae8","source":{"kind":"arxiv","id":"2505.04320","version":1},"attestation_state":"computed","paper":{"title":"Multi-turn Consistent Image Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Tang, Weiming Dong, Xiangyu He, Yingying Deng, Zijun Zhou","submitted_at":"2025-05-07T11:11:23Z","abstract_excerpt":"Many real-world applications, such as interactive photo retouching, artistic content creation, and product design, require flexible and iterative image editing. However, existing image editing methods primarily focus on achieving the desired modifications in a single step, which often struggles with ambiguous user intent, complex transformations, or the need for progressive refinements. As a result, these methods frequently produce inconsistent outcomes or fail to meet user expectations. To address these challenges, we propose a multi-turn image editing framework that enables users to iterativ"},"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":"2505.04320","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-07T11:11:23Z","cross_cats_sorted":[],"title_canon_sha256":"ed75337842877034de6ed0d9f3741d6e61cfddde3053e84f0b1b145ae9c160b1","abstract_canon_sha256":"ce4286632d7beea914b05b6f118a6df694a1066da3957fedd0287ad081bc3249"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:40.002098Z","signature_b64":"jKuppgfbAaZB+WjPfL3JAL9T74PjOYaVS/bT36RVoLki0fGcOSizCaTsUNZxE6lPxC5ZePgpNQBTlXVFsSRwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"876b8f416cd4e13f451f47305263bb69ef777631436c36a86f54687cc4bf4ae8","last_reissued_at":"2026-07-05T10:59:40.001665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:40.001665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-turn Consistent Image Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Tang, Weiming Dong, Xiangyu He, Yingying Deng, Zijun Zhou","submitted_at":"2025-05-07T11:11:23Z","abstract_excerpt":"Many real-world applications, such as interactive photo retouching, artistic content creation, and product design, require flexible and iterative image editing. However, existing image editing methods primarily focus on achieving the desired modifications in a single step, which often struggles with ambiguous user intent, complex transformations, or the need for progressive refinements. As a result, these methods frequently produce inconsistent outcomes or fail to meet user expectations. To address these challenges, we propose a multi-turn image editing framework that enables users to iterativ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04320","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/2505.04320/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":"2505.04320","created_at":"2026-07-05T10:59:40.001729+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.04320v1","created_at":"2026-07-05T10:59:40.001729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04320","created_at":"2026-07-05T10:59:40.001729+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q5VY6QLM2TQT","created_at":"2026-07-05T10:59:40.001729+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q5VY6QLM2TQT6RI7","created_at":"2026-07-05T10:59:40.001729+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q5VY6QLM","created_at":"2026-07-05T10:59:40.001729+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07187","citing_title":"EditVerse3D: High-Quality 3D Object Editing with Region-Aware Learning","ref_index":107,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09233","citing_title":"Towards Robust Sequential Decomposition for Complex Image Editing","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04349","citing_title":"VecSet-Edit: Unleashing Pre-trained LRM for Mesh Editing from Single Image","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09233","citing_title":"Towards Robust Sequential Decomposition for Complex Image Editing","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08029","citing_title":"STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q5VY6QLM2TQT6RI7I4YFEY53NH","json":"https://pith.science/pith/Q5VY6QLM2TQT6RI7I4YFEY53NH.json","graph_json":"https://pith.science/api/pith-number/Q5VY6QLM2TQT6RI7I4YFEY53NH/graph.json","events_json":"https://pith.science/api/pith-number/Q5VY6QLM2TQT6RI7I4YFEY53NH/events.json","paper":"https://pith.science/paper/Q5VY6QLM"},"agent_actions":{"view_html":"https://pith.science/pith/Q5VY6QLM2TQT6RI7I4YFEY53NH","download_json":"https://pith.science/pith/Q5VY6QLM2TQT6RI7I4YFEY53NH.json","view_paper":"https://pith.science/paper/Q5VY6QLM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.04320&json=true","fetch_graph":"https://pith.science/api/pith-number/Q5VY6QLM2TQT6RI7I4YFEY53NH/graph.json","fetch_events":"https://pith.science/api/pith-number/Q5VY6QLM2TQT6RI7I4YFEY53NH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q5VY6QLM2TQT6RI7I4YFEY53NH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q5VY6QLM2TQT6RI7I4YFEY53NH/action/storage_attestation","attest_author":"https://pith.science/pith/Q5VY6QLM2TQT6RI7I4YFEY53NH/action/author_attestation","sign_citation":"https://pith.science/pith/Q5VY6QLM2TQT6RI7I4YFEY53NH/action/citation_signature","submit_replication":"https://pith.science/pith/Q5VY6QLM2TQT6RI7I4YFEY53NH/action/replication_record"}},"created_at":"2026-07-05T10:59:40.001729+00:00","updated_at":"2026-07-05T10:59:40.001729+00:00"}